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

    Neuronpedia

    INDEX
    Explanations

    until a condition is met

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sürekli
    0.50
     nuestra
    0.49
     debemos
    0.47
     kulland
    0.47
     devono
    0.46
     selanjutnya
    0.46
     últimas
    0.46
     prensa
    0.45
     muchos
    0.45
     unserer
    0.45
    POSITIVE LOGITS
    .
    0.46
     그럼
    0.46
    uatu
    0.44
    contrast
    0.44
    ign
    0.44
    total
    0.43
    opaque
    0.43
    wd
    0.43
    合适
    0.43
    beq
    0.42
    Act Density 0.010%

    No Known Activations