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

    Neuronpedia

    INDEX
    Explanations

    distract

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utils
    -0.07
    刚才
    -0.07
    .utf
    -0.06
    BYTES
    -0.06
    aan
    -0.06
     basket
    -0.06
     Mercedes
    -0.06
     Extension
    -0.06
    weak
    -0.06
    .goal
    -0.06
    POSITIVE LOGITS
     "~
    0.07
    enerative
    0.07
    HttpPost
    0.07
     occupied
    0.07
     yoktu
    0.07
    295
    0.07
     гід
    0.06
     reimb
    0.06
    日本
    0.06
     distracted
    0.06
    Act Density 0.010%

    No Known Activations