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

    Neuronpedia

    INDEX
    Explanations

    marginal

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     podkre
    0.69
     яичко
    0.58
     হারা
    0.57
    衄
    0.57
     arrhyth
    0.55
     угро
    0.55
     linkCell
    0.55
     уравнения
    0.55
     Psalms
    0.55
     colorChoice
    0.54
    POSITIVE LOGITS
     marginal
    0.73
    Marg
    0.73
     Marginal
    0.71
     marg
    0.70
     Marg
    0.64
     Margin
    0.60
     Montes
    0.56
     margin
    0.55
    incón
    0.55
    MARGIN
    0.54
    Act Density 0.000%

    No Known Activations