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

    Neuronpedia

    INDEX
    Explanations

    contrast with previous or differing situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     අව
    0.54
     agonist
    0.54
     agon
    0.54
     simulations
    0.53
     excelled
    0.52
    来越
    0.50
    소년
    0.50
     upregulation
    0.50
     motores
    0.50
     pire
    0.49
    POSITIVE LOGITS
    covid
    0.48
    engkap
    0.46
    czes
    0.43
     مند
    0.43
    款式
    0.42
    SetConfig
    0.41
    äm
    0.41
    kende
    0.41
    kovskij
    0.40
    scope
    0.40
    Act Density 0.002%

    No Known Activations