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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    s
    -0.69
    e
    -0.66
    er
    -0.65
    sd
    -0.64
    EndContext
    -0.58
    ی
    -0.58
    quer
    -0.56
     CreateTagHelper
    -0.55
    erta
    -0.53
     betweenstory
    -0.52
    POSITIVE LOGITS
     Efq
    0.82
     Anſ
    0.79
     Theſe
    0.77
     Conſ
    0.75
     Monfieur
    0.72
     Reſ
    0.71
     poffible
    0.69
     purpoſe
    0.68
     myſelf
    0.68
     Diſ
    0.68
    Act Density 0.201%

    No Known Activations