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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rank
    -0.07
    ΣΤ
    -0.07
     mooie
    -0.07
    ASS
    -0.07
     Meal
    -0.06
    [last
    -0.06
     interracial
    -0.06
    _literals
    -0.06
     фінанс
    -0.06
    out
    -0.06
    POSITIVE LOGITS
    /ex
    0.07
     Veterinary
    0.07
     enrol
    0.07
     Velvet
    0.07
     relying
    0.06
    Adresse
    0.06
    Ger
    0.06
     Trong
    0.06
     Whereas
    0.06
     addresses
    0.06
    Act Density 0.000%

    No Known Activations