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

    Neuronpedia

    INDEX
    Explanations

    yield rates, meal prep, online resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    il
    0.54
    ’
    0.49
    ’.
    0.47
    te
    0.46
    ’?
    0.46
    ’:
    0.45
    те
    0.43
    éd
    0.43
    at
    0.43
    nhold
    0.43
    POSITIVE LOGITS
     Corporations
    0.49
    Kappa
    0.47
     Legit
    0.47
     اسماء
    0.46
     panties
    0.46
     Quantification
    0.45
    ﺑ
    0.45
     Individual
    0.45
     Integrative
    0.45
    uiswing
    0.45
    Act Density 0.000%

    No Known Activations