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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hours
    -0.07
    gsub
    -0.07
    警察
    -0.07
    .tab
    -0.07
    .fxml
    -0.07
    _while
    -0.07
    跑
    -0.06
     carpets
    -0.06
    GetWidth
    -0.06
     unaffected
    -0.06
    POSITIVE LOGITS
     nemoh
    0.07
    Comb
    0.06
     своїх
    0.06
    ΗΤ
    0.06
    _OC
    0.06
     :|
    0.05
    astreet
    0.05
    clude
    0.05
    }());↵
    0.05
    YLE
    0.05
    Act Density 0.044%

    No Known Activations