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

    Neuronpedia

    INDEX
    Explanations

    cultural concepts and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     formatos
    0.50
    ᱕
    0.47
    鳗
    0.46
     adicionales
    0.46
    忝
    0.45
    ফর্ম
    0.45
    ೫
    0.44
     ventajas
    0.44
    ocarbon
    0.43
    斻
    0.43
    POSITIVE LOGITS
     k
    0.57
    NE
    0.54
    k
    0.53
     keresztül
    0.52
    n
    0.50
     文化
    0.48
     यांच्या
    0.47
     kautta
    0.45
    rieden
    0.45
     个
    0.44
    Act Density 0.002%

    No Known Activations