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

    Neuronpedia

    INDEX
    Explanations

    conditional programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ”.
    0.77
    నికి
    0.77
    ⁻
    0.74
    ».
    0.74
    ’.
    0.73
     Debt
    0.71
     Apartments
    0.71
    یں۔
    0.70
    ”。
    0.69
     to
    0.68
    POSITIVE LOGITS
     validInput
    0.86
    앉
    0.85
     लैस
    0.79
     পক্ষপাত
    0.79
    orse
    0.79
    চ্ছন্দ
    0.78
     schle
    0.78
     outfitted
    0.77
    座
    0.76
     validated
    0.75
    Act Density 0.003%

    No Known Activations