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

    Neuronpedia

    INDEX
    Explanations

    avoid obvious commenting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aldrig
    0.50
     допомо
    0.47
    Crash
    0.46
     ช่วย
    0.46
     hulp
    0.46
     hjälp
    0.45
     siku
    0.45
     फटाफट
    0.45
     лежит
    0.43
    แรง
    0.43
    POSITIVE LOGITS
     Sustainable
    0.41
    mutate
    0.41
    oured
    0.40
    uiscono
    0.40
    igte
    0.39
     mutating
    0.39
    tmpl
    0.39
    ικού
    0.38
     /$
    0.38
    만에
    0.38
    Act Density 0.001%

    No Known Activations