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

    Neuronpedia

    INDEX
    Explanations

    Roman numerous risks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    の間
    0.57
     )}
    0.51
    برای
    0.51
     arterios
    0.51
     ).
    0.50
     یہودیوں
    0.50
     MBBS
    0.49
    )</
    0.49
    の結果
    0.49
    ૦
    0.49
    POSITIVE LOGITS
    3
    0.61
    2
    0.59
    al
    0.58
    c
    0.57
    it
    0.55
    Т
    0.55
    GO
    0.54
    min
    0.53
    5
    0.52
    portfolio
    0.52
    Act Density 0.000%

    No Known Activations