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

    Neuronpedia

    INDEX
    Explanations

    phrases referencing statistics or numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    following commas or quotation marks

    np_acts-logits-general · gemini-2.0-flash

    list items and clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raiſ
    -1.00
     wikipagina
    -0.97
     Efq
    -0.97
     Theſe
    -0.96
     utafitiHapana
    -0.95
     myſelf
    -0.93
     MainAxisSize
    -0.92
     ſta
    -0.90
     faſt
    -0.88
     Beſ
    -0.88
    POSITIVE LOGITS
     in
    0.60
    ,
    0.54
     at
    0.54
     as
    0.46
     (
    0.45
     with
    0.45
    cfr
    0.43
     —
    0.43
     by
    0.42
    ;
    0.42
    Act Density 0.085%

    No Known Activations