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

    Neuronpedia

    INDEX
    Explanations

    depending on options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Step
    0.62
     STEP
    0.53
    Bước
    0.53
     Bước
    0.49
     Steps
    0.47
     bước
    0.47
    手順
    0.47
     Langkah
    0.46
     steps
    0.45
    STEP
    0.45
    POSITIVE LOGITS
    取决于
    0.50
     choisissez
    0.45
     contextos
    0.45
    options
    0.43
    bation
    0.43
     opções
    0.42
    Bunch
    0.42
    Options
    0.42
     простых
    0.42
     contenders
    0.42
    Act Density 0.010%

    No Known Activations