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

    Neuronpedia

    INDEX
    Explanations

    list item separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     limite
    0.49
     circonstances
    0.46
     descu
    0.45
     décide
    0.45
    ग्रीकल्चर
    0.44
     konsult
    0.44
     procedente
    0.44
     solucionar
    0.43
     instancias
    0.43
     referente
    0.43
    POSITIVE LOGITS
    android
    0.47
    ied
    0.45
    雰囲気
    0.43
     nhưng
    0.42
     +
    0.42
    ษย์
    0.42
    水印
    0.41
    ーム
    0.41
    ICKET
    0.40
    うち
    0.40
    Act Density 0.003%

    No Known Activations