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

    Neuronpedia

    INDEX
    Explanations

    contradictory information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    很可能
    -0.07
    tów
    -0.07
    atars
    -0.07
     Bunny
    -0.07
    AR
    -0.07
    它们
    -0.07
    也都
    -0.07
    フェ
    -0.07
    监事会
    -0.07
     만약
    -0.06
    POSITIVE LOGITS
     Regards
    0.07
    ublic
    0.07
    ليب
    0.06
     qualifier
    0.06
    빌
    0.06
     Plain
    0.06
     Rew
    0.06
     wis
    0.06
     zend
    0.06
    Gov
    0.06
    Act Density 0.032%

    No Known Activations