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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     poisoning
    -0.08
    ครอง
    -0.07
    author
    -0.06
    Italic
    -0.06
    ForResource
    -0.06
    Un
    -0.06
    (Auth
    -0.06
     earm
    -0.06
    Month
    -0.06
    按照
    -0.06
    POSITIVE LOGITS
    owing
    0.07
    ιώ
    0.07
    ём
    0.06
    tz
    0.06
    utom
    0.06
    _svg
    0.06
    чивается
    0.06
    :self
    0.06
     rotor
    0.06
     Crushing
    0.06
    Act Density 0.002%

    No Known Activations