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

    Neuronpedia

    INDEX
    Explanations

    present needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tile
    0.49
     bioqu
    0.48
    yemek
    0.45
     روسی
    0.45
     limon
    0.43
     நீர்
    0.43
     herramientas
    0.43
    शो
    0.43
    cet
    0.43
     золото
    0.43
    POSITIVE LOGITS
    F
    0.55
    B
    0.54
    S
    0.53
    C
    0.52
    N
    0.52
    J
    0.52
    P
    0.50
    Mort
    0.49
    H
    0.47
    จาก
    0.46
    Act Density 0.004%

    No Known Activations