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

    Neuronpedia

    INDEX
    Explanations

    the word "insurance"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    슷
    -0.94
     béton
    -0.80
     تانيه
    -0.78
     Mette
    -0.73
    OGND
    -0.72
     puits
    -0.71
    ękuję
    -0.71
     Putih
    -0.71
    tą
    -0.71
    onite
    -0.69
    POSITIVE LOGITS
     insurance
    0.84
    Insurance
    0.84
     Insurance
    0.80
     insur
    0.73
     INSURANCE
    0.70
     '\\;'
    0.67
    URANCE
    0.66
    ButterKnife
    0.66
    aarrggbb
    0.65
     CSP
    0.64
    Act Density 0.004%

    No Known Activations