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

    Neuronpedia

    INDEX
    Explanations

    classical computing bits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stadiums
    0.55
     compacted
    0.48
     motors
    0.48
     platforms
    0.47
    inya
    0.46
     sectors
    0.46
     cupr
    0.46
     conducting
    0.45
     prosecuted
    0.45
     B
    0.45
    POSITIVE LOGITS
    رير
    0.43
     sinnv
    0.43
    莠
    0.43
    بيت
    0.41
    淹
    0.41
    setType
    0.41
    securityMarks
    0.40
    რთ
    0.39
     ناحيه
    0.39
     Bedeutung
    0.39
    Act Density 0.001%

    No Known Activations