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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inputStream
    -0.07
    /u
    -0.07
     asserts
    -0.06
    ,current
    -0.06
     blow
    -0.06
    ?,
    -0.06
     ebp
    -0.06
     ho
    -0.06
     |\
    -0.06
     persuaded
    -0.06
    POSITIVE LOGITS
     здат
    0.07
    abilirsiniz
    0.06
    mer
    0.06
     meticulous
    0.06
     neust
    0.06
     नद
    0.06
    ustil
    0.06
     resizeMode
    0.06
     Celtic
    0.06
    _trim
    0.06
    Act Density 0.008%

    No Known Activations