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

    Neuronpedia

    INDEX
    Explanations

    improved

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     protects
    -0.06
    _putstr
    -0.06
    (hw
    -0.06
     Polo
    -0.06
     getRandom
    -0.06
    quil
    -0.06
     ust
    -0.06
    /a
    -0.06
     bist
    -0.06
    عاد
    -0.06
    POSITIVE LOGITS
    _credit
    0.07
     DROP
    0.07
    ansas
    0.07
    ड
    0.07
    _browser
    0.06
    SizeMode
    0.06
     XMLHttpRequest
    0.06
    .ACCESS
    0.06
    ﻴ
    0.06
    ально
    0.06
    Act Density 0.007%

    No Known Activations