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

    Neuronpedia

    INDEX
    Explanations

    Vitamin enumerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    loading
    0.43
    nemid
    0.43
    leak
    0.41
     Tapatalk
    0.41
    aptop
    0.40
    ierende
    0.39
    ruff
    0.39
    ufen
    0.39
    保
    0.39
    ľa
    0.38
    POSITIVE LOGITS
    Literatura
    0.42
     бро
    0.41
    شته
    0.40
     Router
    0.38
     тер
    0.38
     enig
    0.38
    BEAN
    0.38
    Hash
    0.37
     jas
    0.37
     trader
    0.37
    Act Density 0.000%

    No Known Activations