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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    !(
    -0.07
     architectures
    -0.06
    灣
    -0.06
    非
    -0.06
    _ignore
    -0.06
     aplicación
    -0.06
     /*↵
    -0.06
     Manifest
    -0.06
     сейчас
    -0.06
     Innovation
    -0.06
    POSITIVE LOGITS
    losed
    0.07
     брон
    0.06
     dimin
    0.06
    mour
    0.06
    =__
    0.06
    Updating
    0.06
    张
    0.06
    692
    0.06
    міну
    0.06
     р
    0.06
    Act Density 0.033%

    No Known Activations