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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     global
    -0.07
     kilomet
    -0.07
    orra
    -0.07
     Vatican
    -0.06
     stderr
    -0.06
     Migration
    -0.06
    500
    -0.06
     hel
    -0.06
    Flags
    -0.06
    $pdf
    -0.06
    POSITIVE LOGITS
    รอง
    0.07
    领域
    0.06
    Shown
    0.06
    .pointer
    0.06
     áll
    0.06
    학과
    0.06
    ография
    0.06
     wir
    0.06
     مجموع
    0.06
    NotBlank
    0.06
    Act Density 0.069%

    No Known Activations