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

    Neuronpedia

    INDEX
    Explanations

    specific foreign characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inversiones
    0.38
    ukup
    0.37
     drivetrain
    0.36
    严
    0.36
     Fot
    0.36
    itteln
    0.36
     inversión
    0.36
     outflows
    0.36
     ≤
    0.35
     बनना
    0.35
    POSITIVE LOGITS
    ^{+}$.
    0.44
    ல்கள்
    0.40
    呈
    0.39
     प्यारी
    0.38
    看
    0.38
    ல்களை
    0.38
    ^{+}$
    0.37
    他人
    0.37
    读
    0.36
     ধরন
    0.36
    Act Density 0.006%

    No Known Activations