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

    Neuronpedia

    INDEX
    Explanations

    rating or score

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atoms
    0.44
     per
    0.41
     molecules
    0.40
     before
    0.39
     if
    0.38
     substances
    0.38
     cases
    0.37
     likelihood
    0.37
     when
    0.37
     $
    0.36
    POSITIVE LOGITS
    Église
    0.41
     Анна
    0.39
     احمد
    0.39
    LEMN
    0.38
    ﮩ
    0.38
    Permissions
    0.37
    Consent
    0.37
     Стро
    0.37
     Tài
    0.37
    Gestion
    0.37
    Act Density 0.000%

    No Known Activations