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

    Neuronpedia

    INDEX
    Explanations

    road, Russian, tailoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ሶ
    0.45
    uestos
    0.45
    려서
    0.45
     Estudios
    0.44
    드
    0.44
    ။
    0.44
    ()?>
    0.43
    ("../
    0.42
    到时候
    0.42
    삭제
    0.42
    POSITIVE LOGITS
    highway
    0.51
     eV
    0.47
     highway
    0.47
     intelligent
    0.45
    hod
    0.43
    intelligent
    0.43
     road
    0.42
     K
    0.42
    hit
    0.42
     доро
    0.41
    Act Density 0.379%

    No Known Activations