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

    Neuronpedia

    INDEX
    Explanations

    a mix of names, tags and legal terms

    oai_token-act-pair · gemini-2.0-flash

    Gonzaga

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ########.
    -0.80
    laint
    -0.76
     coloré
    -0.73
     utafitiHapana
    -0.72
    UIControlState
    -0.72
    UIColor
    -0.71
    RenderAtEndOf
    -0.71
    noopener
    -0.69
     murale
    -0.69
    tamment
    -0.69
    POSITIVE LOGITS
     ―
    0.54
    Izvori
    0.51
     esternos
    0.49
    wieś
    0.46
    </strong>
    0.46
    </em>
    0.45
     ing
    0.45
    lgari
    0.43
    tableFuture
    0.43
     par
    0.41
    Act Density 3.367%

    No Known Activations