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

    Neuronpedia

    INDEX
    Explanations

    say "all"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onian
    -0.08
    cards
    -0.07
    ----↵↵
    -0.07
    258
    -0.07
    isLoading
    -0.07
    Checkpoint
    -0.07
    -----↵
    -0.06
    ení
    -0.06
    >(
    -0.06
     Tabs
    -0.06
    POSITIVE LOGITS
     výše
    0.06
     nové
    0.06
     SAT
    0.06
    .SizeType
    0.06
     archit
    0.06
     synonyms
    0.06
     комму
    0.06
     соврем
    0.06
    .Core
    0.05
    ations
    0.05
    Act Density 0.003%

    No Known Activations