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

    Neuronpedia

    INDEX
    Explanations

    hope this clarifies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     megfelel
    0.68
     ressemble
    0.56
     Tele
    0.55
     exemplify
    0.54
     sera
    0.54
     dele
    0.54
     plaie
    0.53
     ಪುಟ
    0.53
     resemble
    0.53
     obligation
    0.52
    POSITIVE LOGITS
    animations
    0.58
    Dados
    0.54
    now
    0.54
    Makes
    0.53
    ellar
    0.52
    having
    0.51
    Now
    0.50
    NOW
    0.49
    answers
    0.49
     having
    0.49
    Act Density 0.005%

    No Known Activations