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

    Neuronpedia

    INDEX
    Explanations

    built differently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fadeInUp
    0.47
    azoline
    0.46
    ilerini
    0.46
    ந்திய
    0.45
    ıyoruz
    0.43
    asel
    0.42
     ScriptInterface
    0.42
     interdiscipl
    0.42
    irent
    0.42
     Programme
    0.41
    POSITIVE LOGITS
     Kenny
    0.41
     Schwab
    0.40
    0.39
     Benz
    0.37
     Russel
    0.37
     কুমার
    0.36
     LeBron
    0.36
     examples
    0.35
     Phillip
    0.35
     Usman
    0.35
    Act Density 0.000%

    No Known Activations