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

    Neuronpedia

    INDEX
    Explanations

    section breaks or headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ς
    1.74
     anteriores
    1.67
     edizione
    1.51
    கள்
    1.50
    _{-}$
    1.45
    THING
    1.44
    𝐬
    1.41
     semn
    1.38
     anderer
    1.35
    ానికి
    1.34
    POSITIVE LOGITS
    ان
    2.48
    an
    2.38
    на
    2.34
    is
    1.99
    in
    1.80
    न
    1.76
    on
    1.71
    কে
    1.70
    ת
    1.70
    ಾ
    1.70
    Act Density 0.510%

    No Known Activations