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

    Neuronpedia

    INDEX
    Explanations

    file reading and writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ความ
    0.90
     stability
    0.80
    Stability
    0.78
     Stability
    0.75
    背景
    0.72
    、「
    0.71
     چاہی
    0.71
     Comfort
    0.71
     estabilidad
    0.70
    ITHER
    0.70
    POSITIVE LOGITS
    public
    0.88
    file
    0.82
     fileprivate
    0.79
     public
    0.79
    like
    0.74
    setVisible
    0.71
    fish
    0.69
    piece
    0.67
     publicly
    0.66
     públic
    0.66
    Act Density 0.082%

    No Known Activations