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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ücken
    -0.07
    )))),
    -0.06
     Aug
    -0.06
    -0.06
    -0.06
    핀
    -0.06
     вет
    -0.06
     другим
    -0.06
    -0.06
    _format
    -0.06
    POSITIVE LOGITS
    모
    0.07
    -packages
    0.07
     pop
    0.07
    ้↵
    0.06
     cidade
    0.06
     znam
    0.06
    粗
    0.06
     pornost
    0.06
    _Vert
    0.06
     gle
    0.06
    Act Density 0.009%

    No Known Activations