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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Studies
    -0.07
    /Form
    -0.07
    .getPath
    -0.06
     dette
    -0.06
    。「
    -0.06
     WebDriver
    -0.06
     тоді
    -0.06
    ยวก
    -0.06
    borg
    -0.06
     Opcode
    -0.06
    POSITIVE LOGITS
    aneously
    0.06
     tweeted
    0.06
     heiß
    0.06
     stainless
    0.06
    ประ
    0.06
     debunk
    0.06
     wei
    0.06
     страны
    0.06
    异
    0.06
    反
    0.06
    Act Density 0.020%

    No Known Activations