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

    Neuronpedia

    INDEX
    Explanations

    situations and absurdity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     positivos
    0.48
     pouquinho
    0.46
    larınız
    0.46
    あなたの
    0.45
    ющую
    0.45
     entidades
    0.45
     Índice
    0.45
    لار
    0.44
     ваше
    0.44
     religiosos
    0.44
    POSITIVE LOGITS
    us
    0.52
    0
    0.49
    kül
    0.49
    z
    0.49
    io
    0.48
    bus
    0.48
     a
    0.48
    imeter
    0.47
    f
    0.47
    c
    0.46
    Act Density 0.003%

    No Known Activations