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

    Neuronpedia

    INDEX
    Explanations

    code/research context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Coupons
    -0.07
    能看到
    -0.07
    目光
    -0.07
    ܪ
    -0.07
     />'
    -0.07
    .Bounds
    -0.07
     dort
    -0.07
     initi
    -0.07
    🥐
    -0.07
     통해서
    -0.07
    POSITIVE LOGITS
    _take
    0.08
    \$
    0.07
    $,
    0.07
    Testing
    0.07
     Cair
    0.07
     boolean
    0.07
    echo
    0.07
    ToOne
    0.07
    מי
    0.06
    导向
    0.06
    Act Density 0.163%

    No Known Activations