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

    Neuronpedia

    INDEX
    Explanations

    loading indicators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     materials
    -0.06
    ちら
    -0.06
     Students
    -0.06
     regularly
    -0.06
    utdown
    -0.06
    _term
    -0.06
    .products
    -0.06
     geopol
    -0.06
    esimal
    -0.06
    /GPL
    -0.06
    POSITIVE LOGITS
     misdemean
    0.08
    χη
    0.07
    애
    0.06
    logfile
    0.06
     Krist
    0.06
     Bones
    0.06
     parlament
    0.06
     Stoke
    0.06
    caffe
    0.06
     Mirage
    0.06
    Act Density 0.006%

    No Known Activations