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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    blings
    -0.06
     estad
    -0.06
    Species
    -0.06
    stellung
    -0.06
    票
    -0.06
     hovering
    -0.06
    International
    -0.06
     Nep
    -0.06
    international
    -0.06
    Foreign
    -0.06
    POSITIVE LOGITS
    _Msp
    0.07
     هیچ
    0.06
     hf
    0.06
     сни
    0.06
    \\\
    0.06
    -new
    0.06
     Aless
    0.06
    !";↵
    0.06
    자는
    0.06
     low
    0.06
    Act Density 0.336%

    No Known Activations