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

    Neuronpedia

    INDEX
    Explanations

    History, Search, Downloads, flowers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HL
    0.42
     statewide
    0.42
    मधील
    0.39
     simult
    0.38
     simultaneous
    0.38
     Alcohol
    0.38
     Simultaneous
    0.37
     Simult
    0.37
     algéb
    0.37
     tội
    0.36
    POSITIVE LOGITS
    إ
    0.44
     quite
    0.43
    middot
    0.43
    placeholder
    0.41
    empty
    0.41
    quite
    0.41
    setHorizontal
    0.40
    Quite
    0.39
     loading
    0.38
     empty
    0.38
    Act Density 0.000%

    No Known Activations