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

    Neuronpedia

    INDEX
    Explanations

    say "ending in -ile/-styl"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SYM
    -0.07
     sdk
    -0.07
    _comment
    -0.07
    [action
    -0.07
    ρος
    -0.07
    (account
    -0.06
    .cycle
    -0.06
    icí
    -0.06
    武器
    -0.06
    _ACCOUNT
    -0.06
    POSITIVE LOGITS
     pathMatch
    0.06
    _-_
    0.06
     enrich
    0.06
    _import
    0.06
    ??↵↵
    0.06
    [:]↵
    0.06
    inand
    0.06
    _xor
    0.06
    ,↵↵
    0.06
    (',');↵
    0.05
    Act Density 0.203%

    No Known Activations