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

    Neuronpedia

    INDEX
    Explanations

    categories, definitions, and rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Presumably
    0.50
     presumably
    0.50
     hesit
    0.47
    AnimationStyle
    0.47
    although
    0.46
     hesitated
    0.45
    Although
    0.45
     resampling
    0.45
     sarebbero
    0.44
     although
    0.44
    POSITIVE LOGITS
     najważ
    0.51
    Biggest
    0.48
     punishable
    0.47
     you
    0.47
    सबसे
    0.47
     www
    0.46
    Read
    0.46
     Biggest
    0.46
     Criminal
    0.45
     biggest
    0.45
    Act Density 0.024%

    No Known Activations