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

    Neuronpedia

    INDEX
    Explanations

    Parentheses and brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     furry
    -0.07
     sci
    -0.06
     factorial
    -0.06
    (pos
    -0.06
     multiply
    -0.06
     recieved
    -0.06
    pon
    -0.06
    (%
    -0.06
    isors
    -0.06
     moi
    -0.06
    POSITIVE LOGITS
    _shape
    0.07
    .FloatTensor
    0.07
    _BUILD
    0.06
    extras
    0.06
     José
    0.06
    .Button
    0.06
    ,proto
    0.06
    _shortcode
    0.06
     اثر
    0.06
    StrictEqual
    0.06
    Act Density 0.032%

    No Known Activations