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

    Neuronpedia

    INDEX
    Explanations

    blurry cloud or uncertainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    propertyPath
    0.42
     snelheid
    0.42
    theoretical
    0.42
    全程
    0.39
    靈
    0.39
     SPIR
    0.39
     bús
    0.38
     searches
    0.38
     desempenho
    0.38
     WHEN
    0.38
    POSITIVE LOGITS
    下列
    0.47
    ﺫ
    0.43
     nons
    0.43
     Nons
    0.42
     Sant
    0.40
     China
    0.39
     sant
    0.38
     Items
    0.38
    lasm
    0.38
     Smok
    0.38
    Act Density 0.003%

    No Known Activations