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

    Neuronpedia

    INDEX
    Explanations

    foreign language words or code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或者
    0.42
    *,
    0.42
    GPA
    0.41
    явление
    0.41
    си
    0.40
    ща
    0.40
    वरून
    0.40
    PQ
    0.39
    зу
    0.39
    atchewan
    0.39
    POSITIVE LOGITS
     salvar
    0.56
     revêtu
    0.55
     lije
    0.52
     múltiples
    0.50
     într
    0.50
     pièce
    0.50
     reicht
    0.48
     dzie
    0.47
     quella
    0.47
     kär
    0.47
    Act Density 0.000%

    No Known Activations