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

    Neuronpedia

    INDEX
    Explanations

    official site mirrors and logins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    骊
    0.40
    pFile
    0.40
    Gauge
    0.40
     bood
    0.39
     کلی
    0.39
    AssetsRequest
    0.38
    otec
    0.38
    Gaussian
    0.38
    Stack
    0.38
    Pipeline
    0.37
    POSITIVE LOGITS
     login
    0.71
     mirrors
    0.63
     mirror
    0.63
    login
    0.62
     Login
    0.61
    Login
    0.59
     logins
    0.56
     alternatives
    0.55
    ログイン
    0.55
     official
    0.54
    Act Density 0.007%

    No Known Activations