Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Recording/communication information

    np_max-act · gemini-2.0-flash

    instructions related to technical processes and procedures.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on procedural or instructional terms (like “process,” “steps,” “record,” “documentation”) that signal how to carry out tasks.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rup
    -0.07
    jen
    -0.06
     інтерес
    -0.06
     denn
    -0.06
     نیم
    -0.06
    Run
    -0.06
     Simpl
    -0.06
     след
    -0.06
    WM
    -0.06
    華
    -0.06
    POSITIVE LOGITS
    修
    0.07
     accom
    0.06
     Gabri
    0.06
    -col
    0.06
    .EventArgs
    0.06
    имв
    0.06
     pci
    0.06
     onları
    0.06
    (Class
    0.06
    .erb
    0.06
    Act Density 0.070%

    No Known Activations