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

    Neuronpedia

    INDEX
    Explanations

    however, this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Prizes
    0.48
     torsional
    0.45
    🎬
    0.43
     BLOCK
    0.42
    Ω
    0.42
    +,
    0.42
     awkwardly
    0.41
    zo
    0.40
     piqu
    0.39
     glandes
    0.39
    POSITIVE LOGITS
     ఎలాంటి
    0.51
     تعلیم
    0.50
     herhangi
    0.49
     प्यार
    0.47
     wyłącznie
    0.46
     कारवाई
    0.46
    ຂອງທ່ານ
    0.46
    สี
    0.45
     دینے
    0.45
     Màu
    0.45
    Act Density 0.006%

    No Known Activations