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

    Neuronpedia

    INDEX
    Explanations

    a couple of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </h3>
    1.28
    า
    1.13
    یں
    1.12
    asına
    1.09
    </h2>
    1.09
    <0x0D>
    1.09
    1.07
    た
    1.05
    </h4>
    1.03
    ะ
    1.02
    POSITIVE LOGITS
     in
    1.41
    在
    1.41
    5
    1.30
    ك
    1.27
    ه
    1.26
    4
    1.24
    ని
    1.13
     في
    1.13
     interne
    1.08
    ה
    1.08
    Act Density 0.000%

    No Known Activations