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

    Neuronpedia

    INDEX
    Explanations

    this that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    问题
    0.74
    ת
    0.68
    ate
    0.64
    ction
    0.60
    parseFloat
    0.59
    পক্ষ
    0.59
     outra
    0.59
    ed
    0.58
    aklar
    0.57
     svog
    0.57
    POSITIVE LOGITS
     значит
    0.89
    ᴜ
    0.85
     ubiquitin
    0.79
    d
    0.78
     happen
    0.76
    𝒖
    0.72
     inoculation
    0.72
     sabbatical
    0.72
     introduit
    0.72
    ಂಟು
    0.71
    Act Density 0.449%

    No Known Activations