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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _specific
    -0.08
    .Var
    -0.07
    .getLine
    -0.07
     staffing
    -0.06
     Hava
    -0.06
    こんにちは
    -0.06
    _song
    -0.06
    -images
    -0.06
     твор
    -0.06
     veh
    -0.06
    POSITIVE LOGITS
     vä
    0.07
     없다
    0.07
    Codec
    0.07
     فإن
    0.06
     %=
    0.06
     стари
    0.06
    －
    0.06
     Ye
    0.06
    �
    0.06
    sunuz
    0.06
    Act Density 0.072%

    No Known Activations