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

    Neuronpedia

    INDEX
    Explanations

    next

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (column
    -0.07
     Delicious
    -0.07
     Lazar
    -0.07
    count
    -0.06
    (shape
    -0.06
    bian
    -0.06
     Japon
    -0.06
    Pixels
    -0.06
     gland
    -0.06
    STAR
    -0.06
    POSITIVE LOGITS
     equivalents
    0.07
    Delegate
    0.06
     Padding
    0.06
    =n
    0.06
    _Se
    0.06
     successor
    0.06
    _next
    0.06
     olmuştur
    0.06
    _na
    0.06
     necesita
    0.06
    Act Density 0.013%

    No Known Activations