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

    Neuronpedia

    INDEX
    Explanations

    NVMe or Lie algebras

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    なる
    0.62
    <b>
    0.58
    ைக
    0.57
     Mehr
    0.57
    凵
    0.57
    </td>
    0.57
    よ
    0.53
    राव
    0.53
    }.\
    0.53
    豉
    0.52
    POSITIVE LOGITS
     additionally
    0.79
     appreciably
    0.79
     Quite
    0.79
     adventures
    0.78
    ohyd
    0.77
     fashionable
    0.77
     unquestionably
    0.77
     Todas
    0.76
     fabulous
    0.76
    informative
    0.75
    Act Density 0.000%

    No Known Activations