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

    Neuronpedia

    INDEX
    Explanations

    ATED

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     свеж
    -0.06
    _ROUND
    -0.06
    กระท
    -0.06
     Rencontres
    -0.06
     maur
    -0.06
    (correct
    -0.06
    侵
    -0.06
    ові
    -0.06
     OSI
    -0.06
     trous
    -0.06
    POSITIVE LOGITS
     Sit
    0.07
     devised
    0.07
     Ans
    0.06
     swiftly
    0.06
     present
    0.06
     twenty
    0.06
    'It
    0.06
     cock
    0.06
     brushed
    0.06
    Instant
    0.06
    Act Density 0.625%

    No Known Activations