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

    Neuronpedia

    INDEX
    Explanations

    information and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    และ
    0.59
     និង
    0.53
    និង
    0.52
     thiab
    0.49
     மற்றும்
    0.48
     및
    0.47
     и
    0.46
     जितेंद्र
    0.46
     և
    0.46
    及び
    0.45
    POSITIVE LOGITS
    -
    0.44
    μένων
    0.41
     addirittura
    0.40
    த்திலேயே
    0.39
    蟶
    0.39
    这点
    0.39
    ాత్ర
    0.38
     lớn
    0.38
    を買
    0.38
    ILABLE
    0.38
    Act Density 0.040%

    No Known Activations