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

    Neuronpedia

    INDEX
    Explanations

    I prepare to explain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    そのような
    0.40
    дко
    0.39
     empirically
    0.39
     نہیں۔
    0.38
    逻
    0.38
     empirical
    0.37
     ascertaining
    0.37
    Наи
    0.36
    icklabels
    0.36
    PanelVisual
    0.35
    POSITIVE LOGITS
     Prepare
    0.90
     prepare
    0.87
    准备
    0.82
    prepare
    0.80
    準備
    0.78
     buckle
    0.77
    Prepare
    0.75
     brace
    0.73
     준비
    0.73
     Warning
    0.70
    Act Density 0.170%

    No Known Activations