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

    Neuronpedia

    INDEX
    Explanations

    addressing groups what they do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.67
    การ
    0.60
    다고
    0.60
    אָ
    0.57
    も
    0.57
    b
    0.56
    あ
    0.56
    .
    0.55
     bila
    0.55
    ت
    0.55
    POSITIVE LOGITS
     semaines
    0.59
    results
    0.58
    saa
    0.57
     سي
    0.55
     Punkten
    0.55
    يس
    0.55
     أكثر
    0.55
     escalate
    0.55
     Einige
    0.54
    lara
    0.54
    Act Density 0.001%

    No Known Activations