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

    Neuronpedia

    INDEX
    Explanations

    Environments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rowned
    -0.07
    _real
    -0.07
    .existsSync
    -0.07
    ptal
    -0.06
    (signal
    -0.06
     Returned
    -0.06
    Days
    -0.06
     Studies
    -0.06
     ECC
    -0.06
    <long
    -0.06
    POSITIVE LOGITS
         ↵↵
    0.07
     anarchists
    0.07
    ітет
    0.06
    于
    0.06
     yapar
    0.06
     Technician
    0.06
    。那
    0.06
     到
    0.06
    (jTextField
    0.06
    BH
    0.06
    Act Density 0.015%

    No Known Activations