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

    Neuronpedia

    INDEX
    Explanations

    research studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.54
    REDIRECT
    -0.42
     "
    -0.39
    '&:
    -0.38
    انه
    -0.38
    istaa
    -0.37
    ConstraintMaker
    -0.37
    してみてください
    -0.36
    Compact
    -0.35
    zieher
    -0.35
    POSITIVE LOGITS
    parsedMessage
    0.78
     myſelf
    0.74
     itſelf
    0.73
    CppMethod
    0.66
    ftagPool
    0.64
     kasarigan
    0.63
     Anſ
    0.63
     Jefus
    0.61
     juſt
    0.60
    OGND
    0.58
    Act Density 0.009%

    No Known Activations