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

    Neuronpedia

    INDEX
    Explanations

    mental health crisis resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     relaxing
    0.73
     smoot
    0.72
     sleek
    0.69
     sixth
    0.68
     shaded
    0.66
     sprawling
    0.66
     native
    0.65
     smoothness
    0.65
     pacif
    0.64
     telev
    0.64
    POSITIVE LOGITS
     輸入
    0.78
    zám
    0.72
    噩
    0.71
    输入
    0.70
    Massage
    0.68
    روز
    0.68
    EXAMPLE
    0.66
    وارد
    0.66
    的工作
    0.66
    يذ
    0.66
    Act Density 0.054%

    No Known Activations