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

    Neuronpedia

    INDEX
    Explanations

    budget, covering, cache, raced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     微
    0.44
     Micro
    0.43
     温度
    0.43
    Micro
    0.42
     三
    0.41
     temperature
    0.41
     பக
    0.38
    ឡិចត្រូ
    0.38
     micro
    0.37
    7
    0.37
    POSITIVE LOGITS
     genauso
    0.41
     henüz
    0.40
    animity
    0.38
    avais
    0.38
     समस्याएं
    0.38
     domaines
    0.38
    信念
    0.38
    పో
    0.38
    ]=-
    0.38
    oux
    0.37
    Act Density 0.001%

    No Known Activations