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

    Neuronpedia

    INDEX
    Explanations

    requires a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     답변
    0.47
     Opinion
    0.43
     lucid
    0.42
     المزيد
    0.41
     грун
    0.40
     경험
    0.38
     ответы
    0.38
     Expertise
    0.37
     jaoks
    0.37
     ஓர்
    0.36
    POSITIVE LOGITS
    mu
    0.43
    emies
    0.43
     violating
    0.41
    starttime
    0.41
    牴
    0.40
    leding
    0.39
    MU
    0.39
     eléctricas
    0.39
    威力
    0.39
     recta
    0.39
    Act Density 0.002%

    No Known Activations