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

    Neuronpedia

    INDEX
    Explanations

    create

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (station
    -0.07
    .TextImageRelation
    -0.07
     vlas
    -0.07
    indsay
    -0.07
    .'.$
    -0.06
     makeshift
    -0.06
    Abb
    -0.06
    _ru
    -0.06
    aser
    -0.06
    _:*
    -0.06
    POSITIVE LOGITS
     chooser
    0.08
     TXT
    0.07
     Fre
    0.07
    ETY
    0.06
    -drop
    0.06
    rees
    0.06
     goat
    0.06
    tuğ
    0.06
     Зап
    0.06
     çek
    0.06
    Act Density 0.040%

    No Known Activations