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

    Neuronpedia

    INDEX
    Explanations

    call

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rani
    -0.07
     рівень
    -0.07
    '_
    -0.06
    .DataAccess
    -0.06
     duro
    -0.06
    риття
    -0.06
     novamente
    -0.06
    들이
    -0.06
    .accept
    -0.06
    رض
    -0.06
    POSITIVE LOGITS
    ち
    0.07
    نگی
    0.07
    _lookup
    0.07
     �
    0.07
    구
    0.06
    jiang
    0.06
    ata
    0.06
    %↵
    0.06
    (Game
    0.06
    -One
    0.06
    Act Density 0.000%

    No Known Activations