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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron remains inactive (zero‐activation) on all tokens shown, so it does not detect any specific pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    rite
    -0.06
     Gen
    -0.06
    (fin
    -0.06
    .Doc
    -0.06
    مح
    -0.06
    adan
    -0.06
     atroc
    -0.06
     follic
    -0.06
     getCurrent
    -0.06
     ومن
    -0.06
    POSITIVE LOGITS
    indent
    0.07
     NVIDIA
    0.07
    Everyone
    0.06
    ?)
    0.06
    .ForeignKey
    0.06
     gutter
    0.06
     touted
    0.06
    ница
    0.06
     eds
    0.06
    ?$
    0.06
    Act Density 0.001%

    No Known Activations