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

    Neuronpedia

    INDEX
    Explanations

    EST time zone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pemberian
    0.57
     behem
    0.51
     teaser
    0.50
     commander
    0.50
    एस
    0.49
     vaccin
    0.49
     staff
    0.48
    AN
    0.48
     suffoc
    0.48
     drap
    0.48
    POSITIVE LOGITS
     الهواء
    0.50
     ਹੋ
    0.50
    pst
    0.50
     CheckException
    0.49
    Мі
    0.49
     マ
    0.48
     ਗ
    0.48
     ವ
    0.47
     خانواده
    0.46
    |।
    0.46
    Act Density 0.001%

    No Known Activations