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

    Neuronpedia

    INDEX
    Explanations

    prank

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بخ
    -0.07
     went
    -0.07
     أس
    -0.07
     view
    -0.06
     View
    -0.06
    _connection
    -0.06
     erfolgreich
    -0.06
    Learn
    -0.06
    ulers
    -0.06
    badge
    -0.06
    POSITIVE LOGITS
    [length
    0.06
    なの
    0.06
     locations
    0.06
    /values
    0.06
     [/
    0.06
     genel
    0.06
     演
    0.06
    [col
    0.06
    barcode
    0.06
     grads
    0.06
    Act Density 0.003%

    No Known Activations