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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rotation
    -0.06
     ю
    -0.06
    (test
    -0.06
     분류
    -0.06
     bodyParser
    -0.06
    CHAIN
    -0.06
     sarc
    -0.05
     GRA
    -0.05
     annotate
    -0.05
     hello
    -0.05
    POSITIVE LOGITS
    .exam
    0.06
    ária
    0.06
     gsi
    0.06
    unteer
    0.06
    preneur
    0.06
    OperationException
    0.06
    Doing
    0.06
    Svc
    0.06
    받
    0.06
     neue
    0.06
    Act Density 0.193%

    No Known Activations