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

    Neuronpedia

    INDEX
    Explanations

    Time and shift work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     чего
    -0.06
     sincere
    -0.06
     dışarı
    -0.06
     Điều
    -0.06
     Name
    -0.06
     dank
    -0.06
     tỏ
    -0.06
     İki
    -0.06
    .dict
    -0.06
     ingresar
    -0.06
    POSITIVE LOGITS
    (port
    0.07
    APSHOT
    0.06
    累
    0.06
    .MaxLength
    0.06
    .provider
    0.06
    μένος
    0.06
    國際
    0.06
    lung
    0.06
     sarc
    0.06
    σμό
    0.06
    Act Density 0.122%

    No Known Activations