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

    Neuronpedia

    INDEX
    Explanations

    words ending in -on or -ion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    0.47
    elem
    0.47
    d
    0.45
    ele
    0.42
    een
    0.42
    परेशन
    0.42
    ej
    0.41
    letal
    0.40
    მასრულ
    0.39
    dba
    0.39
    POSITIVE LOGITS
    nière
    0.81
    niers
    0.73
    naires
    0.68
    itrile
    0.68
    netje
    0.68
    nement
    0.66
    omics
    0.66
    nier
    0.62
    naire
    0.61
    uclease
    0.60
    Act Density 0.056%

    No Known Activations