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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mayo
    -0.06
     PROP
    -0.06
     MET
    -0.06
    キュ
    -0.06
    िम
    -0.06
    iqu
    -0.06
     CONNECT
    -0.06
     upside
    -0.06
    랍
    -0.06
     continua
    -0.06
    POSITIVE LOGITS
    erving
    0.07
    Runner
    0.07
    _bs
    0.07
     Cute
    0.06
    .Article
    0.06
     then
    0.06
     brazil
    0.06
    ışık
    0.06
    esser
    0.06
     threesome
    0.06
    Act Density 0.000%

    No Known Activations