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

    Neuronpedia

    INDEX
    Explanations

    sudden completeness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     било
    0.41
    ibban
    0.40
     dubious
    0.40
    ்ப்பு
    0.39
     विधाय
    0.39
     జగ
    0.39
     lovable
    0.39
     الجم
    0.38
     била
    0.38
     badan
    0.37
    POSITIVE LOGITS
     rigidity
    0.41
    បន្ទ
    0.39
     invisibility
    0.38
     uncontroll
    0.38
     fever
    0.38
     agreement
    0.37
     disappearance
    0.36
     anguish
    0.36
     未来
    0.36
     confl
    0.35
    Act Density 0.000%

    No Known Activations