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

    Neuronpedia

    INDEX
    Explanations

    Named entities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zar
    -1.95
    ZAR
    -1.29
    zara
    -0.77
    zare
    -0.63
     zar
    -0.62
     Zar
    -0.61
    Zar
    -0.60
    zamos
    -0.59
    s
    -0.59
    zaar
    -0.56
    POSITIVE LOGITS
     houſe
    0.74
     leaſt
    0.70
     $_"
    0.69
     BoxDecoration
    0.69
     pleaſure
    0.67
     Efq
    0.65
    bibfield
    0.63
     Majefty
    0.62
    IntoConstraints
    0.61
    InjectAttribute
    0.60
    Act Density 0.086%

    No Known Activations