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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maxX
    -0.08
    .fill
    -0.07
    $fields
    -0.07
    几分钟
    -0.07
     corner
    -0.06
    ős
    -0.06
    𝘣
    -0.06
    Foto
    -0.06
    බ
    -0.06
     Bul
    -0.06
    POSITIVE LOGITS
    lator
    0.08
     Gender
    0.07
     полов
    0.06
    profiles
    0.06
    .hstack
    0.06
    riteln
    0.06
     huyết
    0.06
    ldre
    0.06
     yaşam
    0.06
     discounted
    0.06
    Act Density 0.001%

    No Known Activations