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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eff
    -0.07
     Ferr
    -0.06
     fol
    -0.06
    selling
    -0.06
    \">\
    -0.06
    :-------------</
    -0.06
     permet
    -0.06
     capability
    -0.06
    欧美
    -0.06
    (Mod
    -0.06
    POSITIVE LOGITS
    truck
    0.08
    atoms
    0.08
    과학
    0.07
    =-=-=-=-=-=-=-=-
    0.07
    蛞
    0.07
    ARSE
    0.07
    .fetchone
    0.07
    Based
    0.07
    go
    0.07
    nosis
    0.07
    Act Density 0.008%

    No Known Activations