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

    Neuronpedia

    INDEX
    Explanations

    understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    heavy
    -0.06
    "a
    -0.06
    relu
    -0.06
    Infrastructure
    -0.06
     ```↵
    -0.06
    ENCE
    -0.06
    .click
    -0.06
     BUS
    -0.06
     calcul
    -0.06
    .good
    -0.06
    POSITIVE LOGITS
    д
    0.07
    .Connect
    0.06
     Blocked
    0.06
    _faces
    0.06
    อนไลน
    0.06
    BYTES
    0.06
     فقد
    0.06
    (Fl
    0.06
     stitching
    0.06
     Supported
    0.06
    Act Density 0.092%

    No Known Activations