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

    Neuronpedia

    INDEX
    Explanations

    chemical compounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pat
    -0.06
     welt
    -0.06
    ност
    -0.06
     misunder
    -0.06
    _avatar
    -0.06
    Crit
    -0.06
    Rec
    -0.06
    Monday
    -0.06
     allowance
    -0.05
     flair
    -0.05
    POSITIVE LOGITS
    剧
    0.07
     brutal
    0.07
    ione
    0.07
     );↵↵↵
    0.07
     příliš
    0.07
     será
    0.07
    printer
    0.07
    iação
    0.06
    .magnitude
    0.06
    -bars
    0.06
    Act Density 0.021%

    No Known Activations