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

    Neuronpedia

    INDEX
    Explanations

    email snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ．
    -1.61
    GraphicsUnit
    -0.82
    -0.80
    AccessorTable
    -0.77
    PerformLayout
    -0.77
    UnusedPrivate
    -0.76
    GTCX
    -0.76
     שוליים
    -0.75
    contentLoaded
    -0.75
    脚注の使い方
    -0.69
    POSITIVE LOGITS
    ;
    0.63
     supérieures
    0.61
    ?
    0.58
    By
    0.55
     réguli
    0.54
     officielle
    0.54
     hason
    0.53
    ()
    0.52
    For
    0.51
     männis
    0.51
    Act Density 0.213%

    No Known Activations