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

    Neuronpedia

    INDEX
    Explanations

    t

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gräns
    -0.65
     igjen
    -0.60
    исленность
    -0.59
     conseguenza
    -0.58
    ArrowToggle
    -0.58
     quelcon
    -0.57
     stället
    -0.54
     héri
    -0.53
     demikian
    -0.52
     risultato
    -0.52
    POSITIVE LOGITS
     even
    0.67
    omitempty
    0.65
    expandindo
    0.62
     EVEN
    0.59
    pecially
    0.55
     NEAR
    0.54
     المعيارى
    0.53
     remotely
    0.53
    Bronnen
    0.52
    lüğ
    0.52
    Act Density 0.005%

    No Known Activations