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

    Neuronpedia

    INDEX
    Explanations

    progress bar percentage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    晔
    0.44
    Teste
    0.42
    Centers
    0.42
     disturbance
    0.39
    enziali
    0.39
    Study
    0.39
    orders
    0.39
    Minimal
    0.39
    మయ్య
    0.39
    ებული
    0.38
    POSITIVE LOGITS
     progress
    1.12
     Progress
    1.03
     progreso
    0.96
    progress
    0.95
    进度
    0.92
    Progress
    0.91
     Fortsch
    0.86
     PROGRESS
    0.82
     ProgressBar
    0.82
    setProgress
    0.80
    Act Density 0.059%

    No Known Activations