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

    Neuronpedia

    INDEX
    Explanations

    consult with professionals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dítě
    0.31
     inhibit
    0.31
     bloodshed
    0.30
     ഇടപെ
    0.29
     দ্বারা
    0.29
     tumult
    0.29
     résult
    0.28
     carelessly
    0.28
     unlink
    0.28
     যখন
    0.28
    POSITIVE LOGITS
     experts
    0.73
     specialists
    0.60
     expertos
    0.59
    experts
    0.59
     esperti
    0.57
     전문가
    0.54
     Experts
    0.54
     professionals
    0.54
    Experts
    0.53
     экспер
    0.53
    Act Density 0.092%

    No Known Activations