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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '">'
    -0.07
    尤
    -0.07
     луч
    -0.07
     babies
    -0.07
    opsis
    -0.07
    -placement
    -0.06
     confessed
    -0.06
    _OscInitStruct
    -0.06
    QUIRES
    -0.06
    licted
    -0.06
    POSITIVE LOGITS
    (logging
    0.08
     revert
    0.07
    战斗力
    0.07
    .setName
    0.07
    .DAY
    0.07
     padx
    0.06
     obr
    0.06
     géné
    0.06
    おります
    0.06
     fueled
    0.06
    Act Density 0.001%

    No Known Activations