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

    Neuronpedia

    INDEX
    Explanations

    fight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shiv
    -0.08
     renderer
    -0.07
    .R
    -0.06
    /libs
    -0.06
     PIPE
    -0.06
     بحث
    -0.06
     اه
    -0.06
     해
    -0.06
     WC
    -0.06
    Monitor
    -0.06
    POSITIVE LOGITS
     чолов
    0.06
    branch
    0.06
     jurors
    0.06
    меч
    0.06
    deal
    0.06
    Disable
    0.05
    템
    0.05
    atcher
    0.05
    ("%.
    0.05
    $$
    0.05
    Act Density 0.038%

    No Known Activations