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

    Neuronpedia

    INDEX
    Explanations

    exponential/explorer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     समीक्षक
    -0.57
     EPA
    -0.54
    EPA
    -0.49
     sürd
    -0.47
     stessi
    -0.46
    va
    -0.46
    WA
    -0.46
     newInstance
    -0.46
     passés
    -0.45
     reparto
    -0.45
    POSITIVE LOGITS
     ſta
    0.85
     raiſ
    0.80
     Reſ
    0.79
     houſe
    0.78
     juſ
    0.77
     uſed
    0.73
     Perſ
    0.72
     myſelf
    0.71
     pleaſure
    0.71
     iſt
    0.71
    Act Density 0.015%

    No Known Activations