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

    Neuronpedia

    INDEX
    Explanations

    encounters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _number
    -0.06
     inspiring
    -0.06
     Hearts
    -0.06
    holds
    -0.06
     Use
    -0.06
     Miracle
    -0.06
    _RDONLY
    -0.06
     WebView
    -0.06
     use
    -0.06
     Golf
    -0.06
    POSITIVE LOGITS
     certainty
    0.07
     blackmail
    0.07
     공간
    0.07
    .iloc
    0.07
     реє
    0.07
     ček
    0.07
     kla
    0.07
     gou
    0.07
     nå
    0.07
     accus
    0.07
    Act Density 0.042%

    No Known Activations