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

    Neuronpedia

    INDEX
    Explanations

    good + luck, judgment, value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Generation
    0.50
    s
    0.49
    sda
    0.48
    0.43
    Difficult
    0.42
    ের
    0.41
    เอียด
    0.41
    繁忙時間服務
    0.40
    ensitive
    0.40
    dN
    0.40
    POSITIVE LOGITS
     खासा
    0.81
     luck
    0.79
    natured
    0.69
    enough
    0.69
     enough
    0.66
    luck
    0.63
     samar
    0.63
     fortune
    0.58
     vibes
    0.58
     Samaritan
    0.58
    Act Density 0.040%

    No Known Activations