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

    Neuronpedia

    INDEX
    Explanations

    percentages and proportions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ference
    0.38
     تقسیم
    0.38
    ेयर
    0.37
    echo
    0.37
    append
    0.36
    count
    0.35
    Echo
    0.35
    raf
    0.34
    entry
    0.34
    (",")
    0.34
    POSITIVE LOGITS
     tzv
    0.39
     survive
    0.38
     Versuch
    0.36
    可能性がある
    0.36
     surveyed
    0.36
     ABV
    0.36
     Kors
    0.35
     Königs
    0.35
     (!)
    0.34
    ʧ
    0.34
    Act Density 0.031%

    No Known Activations