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

    Neuronpedia

    INDEX
    Explanations

    above company

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atletas
    0.48
    y
    0.47
     hábitos
    0.46
     ocorre
    0.44
     sonhos
    0.44
     ketika
    0.44
     attiva
    0.43
     desafíos
    0.43
     în
    0.43
     nên
    0.42
    POSITIVE LOGITS
    ח
    0.49
    ون
    0.46
    на
    0.46
    ის
    0.45
     Bharatiya
    0.44
     typed
    0.43
    ጨማሪ
    0.41
    ంగా
    0.41
    ुत
    0.41
    ర్థ
    0.41
    Act Density 2.920%

    No Known Activations