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

    Neuronpedia

    INDEX
    Explanations

    calculations of amounts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mars
    -0.07
    massage
    -0.07
    every
    -0.07
    .structure
    -0.07
    est
    -0.07
    wiz
    -0.07
     Texture
    -0.07
    ilik
    -0.07
     argument
    -0.07
    bite
    -0.07
    POSITIVE LOGITS
     pening
    0.10
     meningkat
    0.09
    Replacing
    0.09
     replacing
    0.09
     juntar
    0.09
     overwrite
    0.09
     remplacer
    0.08
     artt
    0.08
     ಯೋಜ
    0.08
     darle
    0.08
    Act Density 0.155%

    No Known Activations