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

    Neuronpedia

    INDEX
    Explanations

    a, wide, vast, public, specific, company

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    id
    0.64
     ক্র
    0.50
    OD
    0.49
    URLConnection
    0.46
    ようやく
    0.46
    >'
    0.45
    𝗹
    0.45
    AR
    0.44
    '@
    0.44
    Diaz
    0.44
    POSITIVE LOGITS
     faulty
    0.52
    は何
    0.52
     fancied
    0.50
    在于
    0.50
     rocks
    0.48
    私が
    0.48
     bunches
    0.48
     portes
    0.48
     LOCKED
    0.48
     النقطه
    0.47
    Act Density 1.553%

    No Known Activations