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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cunt
    -0.07
     sav
    -0.06
    rnek
    -0.06
    covers
    -0.06
    _unique
    -0.06
     slou
    -0.06
     mnoha
    -0.06
    _cmp
    -0.06
     gulp
    -0.06
    '][]
    -0.06
    POSITIVE LOGITS
     firebase
    0.07
     reliability
    0.07
    यर
    0.06
     harvested
    0.06
    Modification
    0.06
    ѕ
    0.06
    풍
    0.06
     allowable
    0.06
     Citizenship
    0.06
     Minerals
    0.06
    Act Density 0.000%

    No Known Activations