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

    Neuronpedia

    INDEX
    Explanations

    component template urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    effective
    0.46
     प्रभावी
    0.43
     effective
    0.41
    Effective
    0.41
     albi
    0.41
     टार
    0.40
    ментов
    0.39
     अभिक्रिया
    0.39
    するか
    0.39
     девушка
    0.38
    POSITIVE LOGITS
     SHA
    0.41
    Tok
    0.40
     lógico
    0.40
    SHA
    0.39
     Ae
    0.39
     I
    0.38
     acrobat
    0.38
     শার
    0.37
    Url
    0.37
     ACL
    0.37
    Act Density 0.000%

    No Known Activations