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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    พ
    -0.07
     dece
    -0.06
     arrange
    -0.06
     ISA
    -0.06
    880
    -0.06
    ्बन
    -0.06
    stered
    -0.06
     contest
    -0.06
     NW
    -0.06
    Communic
    -0.06
    POSITIVE LOGITS
     Jeg
    0.06
    [right
    0.06
    ’nın
    0.06
    ’nin
    0.06
    $,
    0.06
     lol
    0.06
    ]$
    0.06
     Porno
    0.06
    Ğ
    0.06
    ğim
    0.06
    Act Density 0.135%

    No Known Activations