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

    Neuronpedia

    INDEX
    Explanations

    ","

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zdroj
    -0.07
    [])
↵
    -0.06
    _jobs
    -0.06
     Cargo
    -0.06
     -------↵
    -0.06
     WORLD
    -0.06
    齐
    -0.06
    "This
    -0.06
    MOOTH
    -0.06
    [word
    -0.06
    POSITIVE LOGITS
     H
    0.07
     blanket
    0.06
    (Event
    0.06
    çois
    0.06
    Fr
    0.06
    Spe
    0.06
     candle
    0.06
     Wei
    0.06
    uggestion
    0.06
    .ST
    0.06
    Act Density 0.008%

    No Known Activations