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

    Neuronpedia

    INDEX
    Explanations

    fantastic recommendation adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ديث
    0.46
     betracht
    0.46
     بیاکت
    0.45
    راہیم
    0.42
     شیع
    0.40
     كلكم
    0.40
     emph
    0.39
     паліты
    0.38
     شرطونه
    0.38
     Eminem
    0.38
    POSITIVE LOGITS
    </strong>
    0.43
    án
    0.43
    ini
    0.42
    afood
    0.41
    לי
    0.41
    vil
    0.41
    ak
    0.40
    res
    0.39
    Float
    0.39
    ina
    0.39
    Act Density 0.002%

    No Known Activations