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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bell
    -0.07
    oshi
    -0.07
     Pis
    -0.07
     damit
    -0.06
    Currency
    -0.06
    amanho
    -0.06
    Wall
    -0.06
     Depression
    -0.06
    _block
    -0.06
    _ITER
    -0.06
    POSITIVE LOGITS
     Plugin
    0.07
    ";}↵
    0.06
    geometry
    0.06
    rgan
    0.06
    _af
    0.06
     paddle
    0.06
     character
    0.06
     Gluten
    0.06
    टर
    0.06
    至少
    0.05
    Act Density 0.037%

    No Known Activations