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

    Neuronpedia

    INDEX
    Explanations

    workflow and organization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     novelle
    -0.09
    енн
    -0.09
    -les
    -0.08
     bırak
    -0.08
    אב
    -0.08
     laisser
    -0.08
     dejan
    -0.08
    нов
    -0.08
    uelle
    -0.08
     lesions
    -0.08
    POSITIVE LOGITS
     Fid
    0.09
    <!--
    0.08
     RTC
    0.07
     fid
    0.07
    」（
    0.07
     fiduci
    0.07
    RT
    0.07
    ··
    0.07
    」「
    0.07
     interpre
    0.06
    Act Density 0.000%

    No Known Activations