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

    Neuronpedia

    INDEX
    Explanations

    version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .SECONDS
    -0.07
    .TextField
    -0.06
     orchestr
    -0.06
    .communic
    -0.06
     př
    -0.06
    accounts
    -0.06
     themed
    -0.06
     件
    -0.06
     ए
    -0.06
    >>()
    -0.06
    POSITIVE LOGITS
     alleen
    0.07
    sphere
    0.07
     excessive
    0.07
    cessive
    0.06
    anchor
    0.06
     Avatar
    0.06
     Dul
    0.06
    rottle
    0.06
    $body
    0.06
     vandalism
    0.06
    Act Density 0.001%

    No Known Activations