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

    Neuronpedia

    INDEX
    Explanations

    list items with leading punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اتھن
    0.29
    ství
    0.28
     diálogo
    0.28
     देसी
    0.27
     licensed
    0.26
    alı
    0.26
    textarea
    0.26
     $(".
    0.26
    गान
    0.25
    羰
    0.25
    POSITIVE LOGITS
     vatth
    0.31
     Katt
    0.30
     Lowe
    0.30
    ახ
    0.30
    zA
    0.29
    textAllCaps
    0.28
     vutt
    0.28
     Pandit
    0.28
     cxd
    0.27
     eP
    0.27
    Act Density 0.000%

    No Known Activations