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

    Neuronpedia

    INDEX
    Explanations

    considered

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    istream
    -0.06
    кан
    -0.06
    custom
    -0.06
     janvier
    -0.06
     spies
    -0.06
    laş
    -0.06
    ]")↵
    -0.06
     tg
    -0.06
    _SEARCH
    -0.06
     primitives
    -0.06
    POSITIVE LOGITS
    ětí
    0.07
    /browser
    0.06
     deficiency
    0.06
    (enc
    0.06
     Peters
    0.06
    apgolly
    0.06
    istics
    0.06
     reliably
    0.06
    erring
    0.06
    豪
    0.06
    Act Density 0.014%

    No Known Activations