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

    Neuronpedia

    INDEX
    Explanations

    electrical measurement and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    frast
    0.45
    頹
    0.44
    leşt
    0.44
     دقی
    0.42
     பார்வை
    0.40
    पिछ
    0.39
    ceva
    0.39
     창
    0.38
    具体的な
    0.38
     développ
    0.38
    POSITIVE LOGITS
    ကယ်
    0.39
    тивов
    0.38
    XH
    0.38
     वाह
    0.38
     SZ
    0.36
     Gypsy
    0.36
    োহর
    0.35
     MW
    0.34
    痔
    0.34
     cards
    0.34
    Act Density 0.001%

    No Known Activations