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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cfg
    -0.07
     moral
    -0.07
    ΟΤ
    -0.06
    letters
    -0.06
     Erot
    -0.06
    _san
    -0.06
    _FOR
    -0.06
     Xml
    -0.06
    ์ต
    -0.06
     Clinton
    -0.06
    POSITIVE LOGITS
    typed
    0.07
    huge
    0.06
    ชน
    0.06
     agricult
    0.06
     geniş
    0.06
     участи
    0.06
     coordinating
    0.06
    提升
    0.06
     opposed
    0.06
     acompañ
    0.06
    Act Density 0.012%

    No Known Activations