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

    Neuronpedia

    INDEX
    Explanations

    present study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    第一次
    -0.74
     Heineken
    -0.74
     Throm
    -0.72
     Last
    -0.71
    isma
    -0.69
    Support
    -0.68
     Transparent
    -0.68
    icot
    -0.68
     Silverstone
    -0.67
     Support
    -0.67
    POSITIVE LOGITS
    هور
    0.75
     ért
    0.73
     biomass
    0.66
    ́
    0.66
    遵
    0.65
    endet
    0.65
    沸
    0.65
    Filing
    0.64
    outez
    0.64
    ardez
    0.64
    Act Density 0.047%

    No Known Activations