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

    Neuronpedia

    INDEX
    Explanations

    reporting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Code
    -0.66
    bacher
    -0.66
     Code
    -0.62
    CODE
    -0.61
     CODE
    -0.57
    ViewInit
    -0.55
    MENTS
    -0.53
    katapos
    -0.53
    ments
    -0.52
    dotenv
    -0.50
    POSITIVE LOGITS
     Eſ
    0.76
     whoſe
    0.72
     ſy
    0.71
    rungsseite
    0.70
     uſed
    0.70
     Efq
    0.69
     متعلقه
    0.69
     Anſ
    0.69
     Monfieur
    0.69
     ―――――
    0.68
    Act Density 0.136%

    No Known Activations