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

    Neuronpedia

    INDEX
    Explanations

    0x hexadecimal values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ka
    0.47
    re
    0.45
     logarithm
    0.43
    argmax
    0.43
    sat
    0.42
    riev
    0.41
    nar
    0.41
    ukhov
    0.40
    nah
    0.40
    unwrap
    0.40
    POSITIVE LOGITS
     persoane
    0.47
     খি
    0.47
     Att
    0.46
     ox
    0.45
    <?
    0.45
     oxen
    0.44
     formação
    0.44
     plantel
    0.44
    जिया
    0.43
     persiapan
    0.43
    Act Density 0.067%

    No Known Activations