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

    Neuronpedia

    INDEX
    Explanations

    const YELP_API_KEY

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unintended
    0.53
     gummies
    0.53
     casinos
    0.52
     dis
    0.52
     midst
    0.51
     frequently
    0.51
     st
    0.50
     sto
    0.50
     twine
    0.50
     fleeting
    0.50
    POSITIVE LOGITS
    Styled
    0.54
     Reise
    0.53
    ütz
    0.50
     iniziare
    0.50
     относя
    0.50
     interrump
    0.49
     ننوت
    0.49
    ེ་
    0.48
     Unterstüt
    0.48
     Neces
    0.47
    Act Density 0.000%

    No Known Activations