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

    Neuronpedia

    INDEX
    Explanations

    linkedin profiles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UMB
    0.40
    uli
    0.38
    iaux
    0.38
    UMP
    0.38
    opor
    0.36
    ombe
    0.35
    ulières
    0.34
    zab
    0.34
    '))
    0.33
    retta
    0.33
    POSITIVE LOGITS
     EventHandler
    0.44
     Psalm
    0.44
     مؤرشف
    0.41
     війни
    0.41
     wrote
    0.40
     Fact
    0.40
     MyBatis
    0.40
     Translated
    0.40
     synovial
    0.39
     význam
    0.38
    Act Density 0.003%

    No Known Activations