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

    Neuronpedia

    INDEX
    Explanations

    product usage limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     citt
    0.48
     ಸದಸ್ಯ
    0.47
     دستاویز
    0.46
    放射
    0.46
     sillas
    0.46
     diagonalization
    0.46
     ধর্ম
    0.44
    鐙
    0.44
    ເລ
    0.44
     molécules
    0.44
    POSITIVE LOGITS
     [
    0.59
     unik
    0.49
    ip
    0.47
    ill
    0.46
     dod
    0.44
     fair
    0.44
     distance
    0.43
     \[
    0.43
     $\
    0.42
     I
    0.42
    Act Density 0.001%

    No Known Activations