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

    Neuronpedia

    INDEX
    Explanations

    titles containing "of"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    0.40
    ترم
    0.40
    μός
    0.39
    Tips
    0.38
    貯
    0.37
     périodes
    0.36
    ور
    0.35
    ]}"
    0.35
    트워크
    0.35
     معانا
    0.35
    POSITIVE LOGITS
     Apollo
    0.46
     Aquarius
    0.43
     Bulgaria
    0.43
     Batman
    0.43
     Superman
    0.43
     Zeus
    0.43
    ūs
    0.42
     Democracy
    0.41
    ussia
    0.40
     Merlin
    0.40
    Act Density 0.008%

    No Known Activations