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

    Neuronpedia

    INDEX
    Explanations

    Technical/Formal Text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.72
     preferring
    -0.67
     متعلقه
    -0.67
     préférence
    -0.65
    ScopeManager
    -0.63
     Зачем
    -0.61
    PreferredItem
    -0.60
    timents
    -0.60
    principalTable
    -0.59
    gestone
    -0.59
    POSITIVE LOGITS
    EndInit
    0.55
     uncertainty
    0.53
     certainty
    0.53
     uncertainties
    0.49
    ToolStripButton
    0.47
     finalmente
    0.42
     friendships
    0.41
    語言
    0.41
    BarButtonItem
    0.41
     Cientí
    0.40
    Act Density 0.003%

    No Known Activations