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

    Neuronpedia

    INDEX
    Explanations

    Command line or code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مکتی
    0.46
    녕하세요
    0.44
    tpVar
    0.39
    aiian
    0.39
    Insect
    0.39
    moda
    0.39
     مذہبی
    0.38
     caracteriza
    0.38
    юд
    0.38
    伟大
    0.38
    POSITIVE LOGITS
     something
    0.47
     seconds
    0.44
     and
    0.43
     attempt
    0.43
     IT
    0.41
     RAT
    0.41
    </
    0.40
     demand
    0.39
     hashed
    0.39
     menit
    0.39
    Act Density 0.000%

    No Known Activations