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

    Neuronpedia

    INDEX
    Explanations

    giving you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ให้กับ
    0.57
     לע
    0.50
    您
    0.50
     बताइए
    0.49
     ભૂ
    0.48
    騁
    0.48
     retra
    0.47
     towering
    0.46
     আপনাকে
    0.46
    でしょうか
    0.46
    POSITIVE LOGITS
    kl
    0.51
    l
    0.50
    et
    0.48
    moja
    0.47
    larni
    0.47
    mog
    0.46
    ా
    0.46
    at
    0.46
    its
    0.45
     Resultado
    0.43
    Act Density 0.100%

    No Known Activations