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

    Neuronpedia

    INDEX
    Explanations

    word

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ζό
    -0.07
     �
    -0.07
    PropertyDescriptor
    -0.06
     entitlement
    -0.06
    internal
    -0.06
     boiled
    -0.06
    لفة
    -0.06
     demonstration
    -0.06
     volunteering
    -0.06
     deliver
    -0.06
    POSITIVE LOGITS
    _def
    0.07
    :def
    0.07
     zm
    0.06
    /fontawesome
    0.06
    /off
    0.06
     RandomForest
    0.06
    .Num
    0.06
    振
    0.06
     Defendants
    0.06
     důvod
    0.06
    Act Density 0.005%

    No Known Activations