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

    Neuronpedia

    INDEX
    Explanations

    to effect change or their safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    1.45
    ли
    1.31
    '
    1.23
    rát
    1.22
    em
    1.19
    ல்
    1.19
    ن
    1.10
    ed
    1.09
    ang
    1.05
    <h4>
    1.04
    POSITIVE LOGITS
    ك
    1.43
    ی
    1.25
     be
    1.23
    י
    1.23
    ي
    1.21
    ق
    1.16
    ח
    1.12
    ;
    1.11
    </strong>
    1.09
     e
    1.09
    Act Density 0.002%

    No Known Activations