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

    Neuronpedia

    INDEX
    Explanations

    formal process requiring hydration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shave
    0.42
     Tạo
    0.41
     تعرض
    0.41
    ेलकम
    0.41
     crawl
    0.40
     Attack
    0.40
     Arabia
    0.40
     මේ
    0.40
     عرب
    0.40
    abhavam
    0.39
    POSITIVE LOGITS
    bl
    0.40
    ottie
    0.38
    hens
    0.38
    kst
    0.37
    کت
    0.37
    dess
    0.35
    jd
    0.35
    jna
    0.35
     maja
    0.35
     evils
    0.35
    Act Density 0.000%

    No Known Activations