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

    Neuronpedia

    INDEX
    Explanations

    integrated information components and status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    釹
    0.39
     LOTRAchievement
    0.37
    Acetic
    0.37
    🫣
    0.36
    堇
    0.36
     Antennes
    0.35
    欳
    0.34
    醀
    0.34
     Clustering
    0.34
    銥
    0.34
    POSITIVE LOGITS
    a
    0.45
    0.42
    p
    0.38
    d
    0.37
    f
    0.37
    i
    0.36
    2
    0.36
    s
    0.36
    h
    0.36
    ip
    0.35
    Act Density 0.000%

    No Known Activations