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

    Neuronpedia

    INDEX
    Explanations

    most

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric expressions—especially decimal numbers and percentages.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     factions
    -0.07
    opened
    -0.06
     Core
    -0.06
    ROL
    -0.06
    _team
    -0.06
    .present
    -0.06
     Zurich
    -0.06
    222
    -0.06
    hof
    -0.06
     achievement
    -0.06
    POSITIVE LOGITS
    WebResponse
    0.07
     amaç
    0.07
    iş
    0.07
     electrom
    0.06
     Iraqi
    0.06
    _attention
    0.06
    orgeous
    0.06
     v�
    0.06
     江
    0.06
    uire
    0.06
    Act Density 0.054%

    No Known Activations