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

    Neuronpedia

    INDEX
    Explanations

    not excessive or typical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uffled
    0.43
     poseb
    0.39
     Solver
    0.37
     Proposed
    0.36
    ваете
    0.35
    endif
    0.35
     विरु
    0.35
    oruč
    0.35
     Tailwind
    0.34
    큘
    0.34
    POSITIVE LOGITS
     conventionally
    0.52
     conventional
    0.48
     elaborate
    0.46
     overtly
    0.46
     glamour
    0.43
    Conventional
    0.42
     कॉम
    0.42
    conventional
    0.41
    複雑
    0.40
     overt
    0.40
    Act Density 0.185%

    No Known Activations