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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations with units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Truthy
    0.43
    媢
    0.41
    ég
    0.39
    plectic
    0.39
    Xét
    0.39
    FlagSet
    0.39
    obili
    0.39
    ケート
    0.38
    ຫຼື
    0.38
     अय्यर
    0.38
    POSITIVE LOGITS
     ≈
    0.55
     =
    0.47
     ÷
    0.43
     >
    0.42
    ≈
    0.40
     ≤
    0.40
     godz
    0.40
     =$
    0.39
     ½
    0.39
     ≠
    0.39
    Act Density 0.036%

    No Known Activations