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

    Neuronpedia

    INDEX
    Explanations

    stat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lena
    0.43
    SpriteCollision
    0.42
    bottlecap
    0.39
     दाल
    0.39
     उत्पाद
    0.38
    нца
    0.37
     mercedes
    0.36
     ক্ষেত্র
    0.36
    шей
    0.35
     চিন
    0.35
    POSITIVE LOGITS
     Staten
    0.84
     stat
    0.62
     STAT
    0.61
    Stat
    0.58
    STAT
    0.58
    stat
    0.57
     Stat
    0.55
     Statutory
    0.49
     Stap
    0.47
     Stain
    0.47
    Act Density 0.005%

    No Known Activations