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

    Neuronpedia

    INDEX
    Explanations

    ability calm actor actor actress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䀒
    0.27
     ⏮
    0.22
    ți
    0.21
    mdash
    0.20
     {
    0.20
     Mathematica
    0.20
    età
    0.19
     এড়িয়ে
    0.19
     м
    0.19
    dB
    0.19
    POSITIVE LOGITS
     colonel
    0.18
    दास
    0.17
     mollus
    0.17
    ష్ట
    0.17
     culto
    0.17
    が出来
    0.17
     ইহাদের
    0.16
     lobster
    0.16
    ុស
    0.16
    Texts
    0.16
    Act Density 0.001%

    No Known Activations