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

    Neuronpedia

    INDEX
    Explanations

    say "div word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    folders
    -0.07
    ockets
    -0.07
    _WINDOW
    -0.06
    kl
    -0.06
     veterinary
    -0.06
    watch
    -0.06
    javascript
    -0.06
     Fry
    -0.06
    vehicle
    -0.06
    áln
    -0.06
    POSITIVE LOGITS
    左
    0.07
    getExtension
    0.07
     Capt
    0.06
     stag
    0.06
    .helper
    0.06
     Gutenberg
    0.06
     leverage
    0.06
    .single
    0.06
    _utf
    0.06
    (mapped
    0.06
    Act Density 0.037%

    No Known Activations