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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash

    This neuron never activates for any token—it doesn’t respond to any pattern (i.e. it’s essentially “dead”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     pathogens
    -0.07
    vit
    -0.06
    파일
    -0.06
     BigDecimal
    -0.06
    ٌ
    -0.06
    olarity
    -0.06
    CLU
    -0.06
    .IndexOf
    -0.06
    Shopping
    -0.06
    romo
    -0.06
    POSITIVE LOGITS
     sister
    0.07
     Delhi
    0.07
    define
    0.07
     Rotation
    0.07
    size
    0.06
     zvyš
    0.06
     Auto
    0.06
     halls
    0.06
     shorter
    0.06
    )}</
    0.06
    Act Density 0.025%

    No Known Activations