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

    Neuronpedia

    INDEX
    Explanations

    real world suggestions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Outcome
    0.41
     પો
    0.40
     ©️
    0.38
     materiality
    0.38
     Routine
    0.37
     bior
    0.37
    မ်
    0.37
     ὁ
    0.37
     sustains
    0.37
     ordinairement
    0.37
    POSITIVE LOGITS
    방법
    0.39
    thar
    0.38
    ppler
    0.38
    ethod
    0.38
    Sci
    0.38
     اخذنا
    0.38
    겁
    0.38
    ism
    0.38
    fail
    0.38
    adis
    0.38
    Act Density 0.000%

    No Known Activations