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

    Neuronpedia

    INDEX
    Explanations

    exclusion and negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     غير
    0.40
    തും
    0.39
     그렇지
    0.38
     nonempty
    0.38
     非
    0.38
     tük
    0.36
    ্যাম্প
    0.36
     headless
    0.35
     nondegenerate
    0.35
     favorita
    0.35
    POSITIVE LOGITS
    atre
    0.38
    FT
    0.35
     धात
    0.35
    nehmen
    0.34
    AN
    0.34
     అత
    0.34
     NOR
    0.34
    cett
    0.33
     hoped
    0.33
     liabilities
    0.33
    Act Density 0.001%

    No Known Activations