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

    Neuronpedia

    INDEX
    Explanations

    expectation, seventh, development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ের
    2.08
    ت
    1.92
    ς
    1.65
    bukti
    1.65
    s
    1.63
    iya
    1.63
    ی
    1.60
    靂
    1.54
    ség
    1.52
    ни
    1.52
    POSITIVE LOGITS
    ka
    1.58
    ki
    1.56
    ற்ப
    1.48
    
    1.47
    .
    1.47
     být
    1.47
    л
    1.46
    Bere
    1.46
     vốn
    1.46
    сть
    1.46
    Act Density 0.000%

    No Known Activations