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

    Neuronpedia

    INDEX
    Explanations

    say currency symbol

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    InRange
    -0.08
     suppose
    -0.08
     whale
    -0.07
    utenberg
    -0.07
    変わって
    -0.07
    .dt
    -0.07
    מרת
    -0.07
    痫
    -0.07
    asInstanceOf
    -0.07
     Shakespeare
    -0.07
    POSITIVE LOGITS
     residency
    0.07
    _mean
    0.07
     Obl
    0.07
    国度
    0.07
    Standard
    0.07
    ſ
    0.07
     женщин
    0.07
    䢼
    0.07
     ..↵↵
    0.07
    Louis
    0.07
    Act Density 0.001%

    No Known Activations