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

    Neuronpedia

    INDEX
    Explanations

    terminology related to mechanical inventions and tools

    oai_token-act-pair · gemini-2.0-flash

    mechanical parts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.96
    +#+#
    -0.66
    AsUp
    -0.65
    перь
    -0.65
    -0.63
    riwal
    -0.62
    ">—
    -0.60
    MLLoader
    -0.59
     passés
    -0.58
    webElementXpaths
    -0.57
    POSITIVE LOGITS
    esgue
    0.47
     soph
    0.44
    straint
    0.43
    compromising
    0.42
     digress
    0.42
    panier
    0.41
     vase
    0.40
    Geografi
    0.40
    vetrain
    0.39
     civilizations
    0.39
    Act Density 21.198%

    No Known Activations