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

    Neuronpedia

    INDEX
    Explanations

    number of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ized
    1.50
    ر
    1.48
    ت
    1.41
    र
    1.31
    er
    1.28
    后
    1.22
    $('
    1.20
    benhav
    1.15
    า
    1.14
    ৭
    1.12
    POSITIVE LOGITS
     fatalities
    1.13
     assures
    1.13
    ਗੇ
    1.10
     deducting
    1.08
     illustrates
    1.06
     eliminates
    1.06
    が多く
    1.06
     disbursements
    1.06
     extrémités
    1.05
     involves
    1.04
    Act Density 0.000%

    No Known Activations