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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cause
    -0.07
     jurors
    -0.07
     Cosmetic
    -0.07
     kayb
    -0.07
    urovision
    -0.07
    anı
    -0.06
    refs
    -0.06
    ρων
    -0.06
     στους
    -0.06
    ampoline
    -0.06
    POSITIVE LOGITS
     bourgeois
    0.07
    _COMPAT
    0.06
    (ml
    0.06
    "}},↵
    0.06
     TextStyle
    0.06
     illusions
    0.06
    aturally
    0.06
    Interval
    0.06
     SUR
    0.06
     CZ
    0.06
    Act Density 0.032%

    No Known Activations