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

    Neuronpedia

    INDEX
    Explanations

    code comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    water
    0.64
    can
    0.59
    స్
    0.58
    ór
    0.56
    veget
    0.55
    োনা
    0.55
    im
    0.54
    os
    0.53
    í
    0.53
    us
    0.52
    POSITIVE LOGITS
     trat
    0.56
     jednu
    0.56
    াক্ষ
    0.54
    thisStudent
    0.54
     FileInputStream
    0.53
    된
    0.53
    のように
    0.52
    تان
    0.52
     துவ
    0.52
     afirm
    0.50
    Act Density 0.001%

    No Known Activations