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

    Neuronpedia

    INDEX
    Explanations

    expressions of admiration or approval

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    impress or impeach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     насељу
    -0.65
     Pardavimas
    -0.60
    <?
    -0.56
     CommonModule
    -0.56
    RectangleBorder
    -0.55
    chieht
    -0.54
    pecabezas
    -0.53
     NavController
    -0.52
    tovers
    -0.51
     PDC
    -0.51
    POSITIVE LOGITS
     isShow
    0.40
    iss
    0.40
     Imp
    0.37
     impressed
    0.36
     impress
    0.35
     Impression
    0.33
    isShow
    0.33
     upon
    0.32
     kasarigan
    0.32
    import
    0.31
    Act Density 0.002%

    No Known Activations