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

    Neuronpedia

    INDEX
    Explanations

    energy, power, electricity, light

    np_acts-logits-general · gemini-2.5-flash-lite

    energy conversion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    с
    0.58
     आंकड़ों
    0.57
    uy
    0.55
     করিয়৷
    0.54
    .~\
    0.52
     содержание
    0.52
     vucc
    0.51
     giường
    0.49
    ۔
    0.49
    0.48
    POSITIVE LOGITS
    ↵↵
    0.88
    a
    0.78
     energía
    0.74
    ה
    0.73
     you
    0.73
     energia
    0.73
    א
    0.71
    я
    0.68
     energy
    0.68
    n
    0.64
    Act Density 0.903%

    No Known Activations