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

    Neuronpedia

    INDEX
    Explanations

    positive descriptions of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     एवं
    1.13
    および
    1.11
     and
    1.05
     homogene
    0.94
     および
    0.94
    及び
    0.93
     estremamente
    0.92
     및
    0.92
     altamente
    0.92
    and
    0.90
    POSITIVE LOGITS
     whatnot
    0.92
     meds
    0.91
    Whatever
    0.89
     др
    0.84
     ஏதாவது
    0.84
     тоже
    0.84
     Whatever
    0.82
    何か
    0.82
     계속
    0.82
    モニター
    0.80
    Act Density 0.227%

    No Known Activations