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

    Neuronpedia

    INDEX
    Explanations

    cell division

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    0.50
     ਲ
    0.49
    TabStop
    0.48
     }^{
    0.48
     unsteady
    0.48
    kal
    0.47
    i
    0.47
    ມ
    0.46
    otho
    0.45
    𝓛
    0.45
    POSITIVE LOGITS
    ة
    0.63
     calcular
    0.59
    ítica
    0.58
    ática
    0.57
     matriz
    0.57
    分裂
    0.57
    тяги
    0.56
    ubic
    0.55
    ាញ់
    0.54
    liquidacion
    0.53
    Act Density 0.001%

    No Known Activations