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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _more
    -0.07
     Opport
    -0.07
     푸
    -0.06
    <?>>
    -0.06
    นม
    -0.06
     وسی
    -0.06
     grap
    -0.06
    Pos
    -0.06
     육
    -0.06
    ="<
    -0.06
    POSITIVE LOGITS
     شناسی
    0.06
     Championships
    0.06
    orea
    0.06
    oving
    0.06
     latitude
    0.06
     Serialize
    0.06
     Serialized
    0.06
    iconductor
    0.06
     helping
    0.06
    /py
    0.06
    Act Density 0.000%

    No Known Activations