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

    Neuronpedia

    INDEX
    Explanations

    Engine repair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autoplay
    -0.09
     decentralized
    -0.08
     műkö
    -0.08
     mouv
    -0.08
     decentral
    -0.08
    Simple
    -0.08
     pleasant
    -0.08
    Truthy
    -0.08
     dek
    -0.08
    Autocomplete
    -0.08
    POSITIVE LOGITS
     exorbit
    0.08
     rents
    0.08
    iceps
    0.07
     altas
    0.07
    _bounds
    0.07
     fabricantes
    0.07
    昂
    0.07
     Gifts
    0.07
     Bulls
    0.07
     bulld
    0.07
    Act Density 0.018%

    No Known Activations