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

    Neuronpedia

    INDEX
    Explanations

    grasshopper and variable declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arousal
    0.61
     अर्जुन
    0.59
    t
    0.59
    elige
    0.58
    ti
    0.58
     Mudah
    0.58
     оце
    0.57
    gó
    0.57
    the
    0.57
     afront
    0.56
    POSITIVE LOGITS
    )
    0.64
    NON
    0.62
     بیمار
    0.60
    IEEE
    0.58
    FA
    0.58
    ור
    0.57
    Alleg
    0.57
    و
    0.56
    ו
    0.54
    놁
    0.54
    Act Density 0.001%

    No Known Activations