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

    Neuronpedia

    INDEX
    Explanations

    acetylcholine, import, stats, TE

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ول
    0.67
    :
    0.54
    AR
    0.52
    I
    0.51
     r
    0.48
    ):
    0.46
    ),
    0.45
    r
    0.45
    ;
    0.44
    ra
    0.44
    POSITIVE LOGITS
    на
    0.81
    ى
    0.67
     can
    0.67
    ли
    0.61
    고
    0.57
    но
    0.57
    um
    0.55
    та
    0.55
    و
    0.55
    čnom
    0.55
    Act Density 0.024%

    No Known Activations