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

    Neuronpedia

    INDEX
    Explanations

    .Model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fullWidth
    -0.06
    IPHER
    -0.06
    IALIZ
    -0.06
    birthday
    -0.06
    51
    -0.06
    Suite
    -0.06
     博
    -0.06
     dispon
    -0.06
     janvier
    -0.06
     Pills
    -0.06
    POSITIVE LOGITS
    .Model
    0.17
     Claudia
    0.12
     grayscale
    0.09
    .Method
    0.09
     Julia
    0.09
    dehyde
    0.08
    .writerow
    0.08
     investments
    0.07
    _PED
    0.07
    .Child
    0.07
    Act Density 0.003%

    No Known Activations