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

    Neuronpedia

    INDEX
    Explanations

    .com/ or .jpg"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PhysRev
    0.44
     비용
    0.35
    <unused2188>
    0.35
    리면
    0.34
    getMeteringAreas
    0.34
    PolicyQuery
    0.34
    MouseMove
    0.34
     که
    0.34
    しますが
    0.34
    ۔
    0.33
    POSITIVE LOGITS
     be
    0.63
     for
    0.62
     had
    0.50
    ↵
    0.49
    n
    0.49
     and
    0.48
    in
    0.48
    u
    0.47
    L
    0.46
     el
    0.43
    Act Density 0.551%

    No Known Activations