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

    Neuronpedia

    INDEX
    Explanations

    coding/scripting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     servant
    -0.08
    ceptors
    -0.07
    volent
    -0.07
     Rune
    -0.07
     Axios
    -0.07
    curity
    -0.07
    像是
    -0.07
     refs
    -0.06
    _commit
    -0.06
    <main
    -0.06
    POSITIVE LOGITS
    moved
    0.07
     shoes
    0.07
    ulled
    0.07
    实实在在
    0.06
     WAY
    0.06
    처리
    0.06
     Söz
    0.06
    quoted
    0.06
    olynomial
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations