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

    Neuronpedia

    INDEX
    Explanations

    specific items

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hộ
    0.61
     ağ
    0.59
    ه‌ها
    0.58
    ậ
    0.58
     ARTHUR
    0.57
    aldb
    0.57
    غاز
    0.56
    ewód
    0.56
    ه‌های
    0.55
    ssh
    0.55
    POSITIVE LOGITS
     immersion
    0.62
     Item
    0.61
     Höhen
    0.60
     specif
    0.57
    也很
    0.56
     item
    0.55
    ValueSet
    0.54
     noted
    0.53
     immersed
    0.53
     soon
    0.52
    Act Density 0.000%

    No Known Activations