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

    Neuronpedia

    INDEX
    Explanations

    changes made

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.52
     एवं
    0.48
     বিগত
    0.46
     ಹಾಗೂ
    0.44
     आणि
    0.44
    sequent
    0.43
    and
    0.41
    ≃
    0.41
    ⇉
    0.41
    ade
    0.40
    POSITIVE LOGITS
     inplace
    0.41
     ocup
    0.39
     allocations
    0.38
     sprays
    0.38
    ூழ
    0.38
     значений
    0.38
     ойношот
    0.37
     winds
    0.37
     multiplicação
    0.37
     coef
    0.37
    Act Density 0.005%

    No Known Activations