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

    Neuronpedia

    INDEX
    Explanations

    highly recommend with exclamations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     일반적으로
    0.42
     մաս
    0.42
     பெரும்பாலும்
    0.39
     பொதுவாக
    0.38
    간
    0.38
     ಅದನ್ನು
    0.38
    धीरे
    0.37
     সাধারণত
    0.36
     ስለ
    0.35
     단계
    0.35
    POSITIVE LOGITS
     !!!!!
    0.50
     )
    0.43
     segunda
    0.42
     tycoon
    0.42
    !!!!
    0.42
     rs
    0.41
    ‬
    0.41
    :-)
    0.41
    !!!!!
    0.41
     oh
    0.40
    Act Density 0.001%

    No Known Activations