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

    Neuronpedia

    INDEX
    Explanations

    serious issues or code analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    おそらく
    0.47
    સ્ટ
    0.47
    다면
    0.46
    তাই
    0.45
    ফেসর
    0.45
    τροπ
    0.45
    titan
    0.44
    arctan
    0.43
    ᱮ
    0.43
    र्ख
    0.43
    POSITIVE LOGITS
     mutilated
    0.51
    ir
    0.50
     няма
    0.49
     els
    0.49
     detal
    0.48
     grossesse
    0.47
     évaluation
    0.47
     organise
    0.46
     ordinaire
    0.45
    ng
    0.45
    Act Density 0.002%

    No Known Activations