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

    Neuronpedia

    INDEX
    Explanations

    sampling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SpecWarn
    -0.07
     bảng
    -0.06
     organs
    -0.06
     Killed
    -0.06
     nostro
    -0.06
    :.:.:.:.:
    -0.06
    .SwingConstants
    -0.06
    飾
    -0.06
    _strip
    -0.06
     Cupertino
    -0.06
    POSITIVE LOGITS
     sampling
    0.09
    501
    0.07
    (Call
    0.07
    FM
    0.07
     Sampling
    0.06
     senate
    0.06
     sampled
    0.06
     Carolyn
    0.06
     Amateur
    0.06
    (Customer
    0.06
    Act Density 0.008%

    No Known Activations