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

    Neuronpedia

    INDEX
    Explanations

    academic/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     کوت
    -0.07
    oned
    -0.07
     ไ
    -0.07
     Student
    -0.07
     CCT
    -0.07
    alone
    -0.06
     Razor
    -0.06
     bigot
    -0.06
     knocking
    -0.06
    anth
    -0.06
    POSITIVE LOGITS
    Perform
    0.06
     Territory
    0.06
    contexts
    0.06
    ropriate
    0.06
    _internal
    0.06
    십
    0.06
     ")"
    0.06
    0.06
     incompatible
    0.06
     booths
    0.06
    Act Density 0.000%

    No Known Activations