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

    Neuronpedia

    INDEX
    Explanations

    an evening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Integer
    0.49
     Exec
    0.46
     ord
    0.43
    Integer
    0.42
    Cox
    0.40
     Cox
    0.40
    cox
    0.38
     coerce
    0.38
     longiore
    0.38
    強制
    0.37
    POSITIVE LOGITS
     cathedral
    0.39
    arrison
    0.37
    ଧ
    0.37
     Cathedral
    0.37
    ੍ਹ
    0.37
    ossing
    0.36
    きましたが
    0.36
     tribe
    0.35
    ệ
    0.35
     आग
    0.35
    Act Density 0.033%

    No Known Activations