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

    Neuronpedia

    INDEX
    Explanations

    secretly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ver
    -0.06
    igor
    -0.06
     кры
    -0.06
    .getDrawable
    -0.06
    ьогод
    -0.06
     nhựa
    -0.06
    unn
    -0.06
    .amazon
    -0.06
    �
    -0.06
    爵
    -0.06
    POSITIVE LOGITS
     Dys
    0.06
     glut
    0.06
    _instr
    0.06
     dio
    0.06
    ќ
    0.06
     sulph
    0.06
    EXAMPLE
    0.06
    ısından
    0.06
    .While
    0.06
    орош
    0.06
    Act Density 0.016%

    No Known Activations