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

    Neuronpedia

    INDEX
    Explanations

    vehicles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Bunifu
    -0.07
     SIGN
    -0.07
     等
    -0.07
     씨
    -0.07
     住
    -0.06
    ك
    -0.06
    Sadly
    -0.06
     lors
    -0.06
    zdy
    -0.06
     TORT
    -0.06
    POSITIVE LOGITS
    ':[
    0.07
    .absolute
    0.07
    [c
    0.06
    (proj
    0.06
    (tf
    0.06
    ْن
    0.06
    research
    0.06
    setText
    0.06
     offsetof
    0.06
     epidemic
    0.06
    Act Density 0.017%

    No Known Activations