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

    Neuronpedia

    INDEX
    Explanations

    a or an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     behave
    -0.07
     shepherd
    -0.07
     بها
    -0.07
     DMA
    -0.07
    -outs
    -0.06
    νον
    -0.06
     hardwood
    -0.06
    सर
    -0.06
    BY
    -0.06
    -wheel
    -0.06
    POSITIVE LOGITS
     خدم
    0.06
    (language
    0.06
    (qu
    0.06
    plied
    0.06
    (short
    0.06
     illum
    0.06
    piar
    0.06
    <article
    0.06
    etro
    0.06
    $c
    0.06
    Act Density 0.008%

    No Known Activations