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

    Neuronpedia

    INDEX
    Explanations

    Tr, Cr, Arr, Fr beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    e
    0.91
    eh
    0.85
    eb
    0.78
    ــــ
    0.77
    ebe
    0.77
    ᱽ
    0.76
    es
    0.76
     단
    0.75
    yas
    0.73
    ส์
    0.73
    POSITIVE LOGITS
    hythm
    1.34
    agment
    1.29
    incipal
    1.29
    acing
    1.19
    ushed
    1.18
    acking
    1.18
    agedy
    1.15
    ubber
    1.12
    idge
    1.11
    rrrr
    1.11
    Act Density 0.180%

    No Known Activations