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

    Neuronpedia

    INDEX
    Explanations

    common vulnerabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    qr
    0.50
    expanded
    0.42
     الشه
    0.41
     বুঝ
    0.40
    telefone
    0.40
    umsuz
    0.40
    fp
    0.39
    correlation
    0.39
    insurer
    0.39
    ncoder
    0.39
    POSITIVE LOGITS
     remit
    0.46
     traps
    0.44
    亢
    0.42
     fores
    0.41
    ífico
    0.41
     modules
    0.41
     policy
    0.40
     orbits
    0.40
    이라면
    0.40
     rem
    0.40
    Act Density 6.013%

    No Known Activations