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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '_'
    -0.07
    Раз
    -0.07
     Ethiopia
    -0.07
    戲
    -0.07
    ина
    -0.06
     FirstName
    -0.06
    лад
    -0.06
     Ler
    -0.06
     ecstasy
    -0.06
    tam
    -0.06
    POSITIVE LOGITS
    (BitConverter
    0.06
    _STATE
    0.06
    ?action
    0.06
     pronounce
    0.06
     emailing
    0.06
    imits
    0.06
     Şubat
    0.06
    _DM
    0.06
    "]
↵
    0.06
     Contrast
    0.06
    Act Density 0.023%

    No Known Activations