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

    Neuronpedia

    INDEX
    Explanations

    gi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Clazz
    -0.07
    Gr
    -0.07
     Soda
    -0.07
     floods
    -0.07
     Dublin
    -0.06
     Hey
    -0.06
    -ing
    -0.06
    TRA
    -0.06
    ्पत
    -0.06
    nů
    -0.06
    POSITIVE LOGITS
    ın
    0.08
     значит
    0.07
    (console
    0.07
     와
    0.07
    encia
    0.07
    =target
    0.06
    .TabControl
    0.06
    parison
    0.06
     (↵↵
    0.06
    _hint
    0.06
    Act Density 0.001%

    No Known Activations