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

    Neuronpedia

    INDEX
    Explanations

    factual information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.78
     ivelany
    -0.76
     ComVisible
    -0.73
    ########.
    -0.68
     metaphors
    -0.66
    )‏
    -0.66
    حياتها
    -0.66
     speeches
    -0.65
     nahilalakip
    -0.65
    ⓧ
    -0.64
    POSITIVE LOGITS
     review
    0.56
     esprits
    0.55
     modalités
    0.53
     prisonniers
    0.53
     spectateurs
    0.52
     âmes
    0.50
    ímetros
    0.49
     consommateurs
    0.49
     églises
    0.49
     bienfaits
    0.49
    Act Density 0.092%

    No Known Activations