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

    Neuronpedia

    INDEX
    Explanations

    science articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RFC
    -0.07
     FIXME
    -0.07
     kicker
    -0.07
    امبر
    -0.07
    Duplicates
    -0.07
     трет
    -0.06
     component
    -0.06
    посеред
    -0.06
     Ernst
    -0.06
     виснов
    -0.06
    POSITIVE LOGITS
     hodně
    0.07
    .="
    0.06
    ollect
    0.06
    陵
    0.06
    ']}'
    0.06
    _WATCH
    0.06
    215
    0.06
     Volunteer
    0.05
    904
    0.05
    682
    0.05
    Act Density 0.039%

    No Known Activations