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

    Neuronpedia

    INDEX
    Explanations

    I am / I want / I can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.62
     School
    0.55
    aniu
    0.53
    iet
    0.52
     $(<
    0.52
     Soup
    0.52
     Gros
    0.51
    elés
    0.51
    ia
    0.50
    TypeCode
    0.50
    POSITIVE LOGITS
     допомогти
    0.62
     rivalry
    0.59
     telah
    0.58
     ช่วย
    0.57
    ceği
    0.56
     injuring
    0.55
     bertanya
    0.55
     గురించి
    0.55
    するので
    0.55
     robbery
    0.54
    Act Density 0.135%

    No Known Activations