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

    Neuronpedia

    INDEX
    Explanations

    ordinal day numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.49
     .
    0.46
    can
    0.44
    क
    0.43
    cd
    0.41
    we
    0.38
    />
    0.37
    8
    0.37
    ()
    0.36
    cz
    0.36
    POSITIVE LOGITS
    کروچ
    0.43
    匤
    0.41
     решать
    0.40
    bruch
    0.40
    󠁥
    0.40
     جائیں
    0.39
    úrg
    0.39
    ColorBit
    0.39
    adeso
    0.39
     Geschä
    0.38
    Act Density 0.001%

    No Known Activations