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

    Neuronpedia

    INDEX
    Explanations

    affect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     affect
    -0.93
    FormTagHelper
    -0.59
    affect
    -0.59
     impact
    -0.57
     Affect
    -0.57
    Становништво
    -0.55
     kanssa
    -0.50
    dji
    -0.48
     effect
    -0.47
    impact
    -0.45
    POSITIVE LOGITS
     firſt
    0.94
     myſelf
    0.94
     Anſ
    0.93
     ſta
    0.91
     Monfieur
    0.91
     Efq
    0.90
     leaſt
    0.89
     ſeveral
    0.89
    SourceChecksum
    0.86
     becauſe
    0.84
    Act Density 0.652%

    No Known Activations