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

    Neuronpedia

    INDEX
    Explanations

    science/studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -0.92
     auffi
    -0.84
     ſche
    -0.79
     raiſ
    -0.75
     faſt
    -0.73
     ſind
    -0.72
     Eſ
    -0.71
     autorytatywna
    -0.71
     Houſe
    -0.70
     Monfieur
    -0.69
    POSITIVE LOGITS
    SourceChecksum
    0.61
     ExecuteAsync
    0.56
     ny
    0.54
    な
    0.52
    unched
    0.52
    SuspendLayout
    0.51
    ated
    0.50
    entas
    0.49
     connexe
    0.49
    ded
    0.48
    Act Density 0.048%

    No Known Activations