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

    Neuronpedia

    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RC
    -0.08
    or
    -0.06
    “For
    -0.06
    moved
    -0.06
     rud
    -0.06
    195
    -0.06
    hores
    -0.06
    ULAR
    -0.06
    ipes
    -0.06
     　
    -0.06
    POSITIVE LOGITS
    //--------------------------------------------------------------↵
    0.07
    .points
    0.06
    @interface
    0.06
    stantiateViewController
    0.06
    lesia
    0.06
    choices
    0.06
    ;(
    0.06
    <<<
    0.06
    #[
    0.06
    CKET
    0.06
    Act Density 0.000%

    No Known Activations