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

    Neuronpedia

    INDEX
    Explanations

    boolean values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    們
    0.40
    oucester
    0.40
    の手
    0.40
    勉
    0.38
    梼
    0.38
     विनो
    0.38
    生まれた
    0.38
    Mein
    0.38
    蚣
    0.38
    হাত
    0.38
    POSITIVE LOGITS
     false
    1.93
     true
    1.81
     False
    1.73
    false
    1.68
     True
    1.66
    False
    1.60
     TRUE
    1.59
    true
    1.56
     FALSE
    1.52
    FALSE
    1.49
    Act Density 0.097%

    No Known Activations