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

    Neuronpedia

    INDEX
    Explanations

    King Jr

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Magellan
    2.15
     বলিয়াই
    2.03
     žel
    1.98
     dichos
    1.96
     poking
    1.91
     اعرف
    1.87
     η
    1.85
    숍
    1.85
     webdriver
    1.84
    ’’
    1.84
    POSITIVE LOGITS
    म
    2.19
    आ
    2.02
    ज
    1.89
    atás
    1.81
    an
    1.76
    تس
    1.73
    loads
    1.67
    पणे
    1.65
    чение
    1.65
    ১৮
    1.63
    Act Density 0.000%

    No Known Activations