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

    Neuronpedia

    INDEX
    Explanations

    image dimensions like 800px

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     നീ
    0.71
    乱
    0.65
     Poem
    0.61
     особенно
    0.60
     केले
    0.60
     especially
    0.59
    ु
    0.59
     occupancy
    0.59
    亂
    0.59
     might
    0.58
    POSITIVE LOGITS
     spermatozoa
    0.79
    ijnen
    0.78
     biliary
    0.77
    éro
    0.76
    èr
    0.74
    utches
    0.72
    _'+
    0.72
    କୁ
    0.71
     Prothorax
    0.71
     Mayweather
    0.71
    Act Density 0.002%

    No Known Activations