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

    Neuronpedia

    INDEX
    Explanations

    ease or difficulty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .lin
    -0.07
     torso
    -0.07
     mohli
    -0.06
    лара
    -0.06
    �
    -0.06
    yre
    -0.06
     Pilot
    -0.06
     Evans
    -0.06
    iliated
    -0.06
     Leia
    -0.06
    POSITIVE LOGITS
    elog
    0.07
    Он
    0.06
     tant
    0.06
    мон
    0.06
     внут
    0.06
    _FLAGS
    0.06
    .Nome
    0.06
    parison
    0.06
    ')));↵↵
    0.06
     wealthy
    0.06
    Act Density 0.056%

    No Known Activations