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

    Neuronpedia

    INDEX
    Explanations

    words-connected-by-hyphens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dragState
    1.10
     dwRes
    1.07
     Labrenzia
    1.01
     杯
    1.01
     GPU
    0.99
     BOARDSIZE
    0.98
     ANOVA
    0.98
     CentOS
    0.97
    悗
    0.97
     Cashback
    0.95
    POSITIVE LOGITS
    -
    3.44
    -(
    2.02
    -.
    1.96
    -...
    1.93
    -%
    1.85
    -'
    1.83
    -,
    1.70
    -*
    1.67
    ()-
    1.66
    -:
    1.63
    Act Density 0.201%

    No Known Activations