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

    Neuronpedia

    INDEX
    Explanations

    technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.62
     Exacts
    -0.60
     bezeichneter
    -0.58
    GraphicsUnit
    -0.56
    bewerken
    -0.52
    twimg
    -0.49
     CURLOPT
    -0.49
    rungsseite
    -0.48
     NgModule
    -0.47
    tagez
    -0.47
    POSITIVE LOGITS
     Margin
    0.61
    зулта
    0.61
    rrggbb
    0.59
    principalTable
    0.57
     margin
    0.56
    calaure
    0.55
    AddField
    0.52
     Factor
    0.52
     Anti
    0.50
    cotta
    0.50
    Act Density 0.000%

    No Known Activations