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

    Neuronpedia

    INDEX
    Explanations

    ud, ed, d

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     north
    -0.07
    �
    -0.06
     south
    -0.06
     chain
    -0.06
    Language
    -0.06
     ниже
    -0.06
    (line
    -0.06
     arrog
    -0.06
    _back
    -0.06
    _pushButton
    -0.06
    POSITIVE LOGITS
    дов
    0.08
     Zack
    0.07
    ์ร
    0.06
    -ranked
    0.06
    celed
    0.06
    lardır
    0.06
    abcd
    0.06
    ND
    0.06
    ker
    0.06
    _pal
    0.06
    Act Density 0.007%

    No Known Activations