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

    Neuronpedia

    INDEX
    Explanations

    os.makedirs(

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    drawn
    1.86
    രുവനന്തപു
    1.85
    锢
    1.81
    1.79
    ⱼ
    1.77
     cbind
    1.77
    drawable
    1.76
    dish
    1.73
    findOrFail
    1.72
    displays
    1.70
    POSITIVE LOGITS
     derin
    1.72
    iyat
    1.71
     olun
    1.70
     harap
    1.70
    પ
    1.70
    ive
    1.65
    ו
    1.61
    ل
    1.60
    র্ড
    1.59
    Р
    1.59
    Act Density 0.001%

    No Known Activations