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

    Neuronpedia

    INDEX
    Explanations

    tickets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     London
    -0.79
     transitions
    -0.68
     ticket
    -0.64
     collision
    -0.64
    AttributeSet
    -0.62
     tickets
    -0.61
     transition
    -0.59
     Work
    -0.59
    London
    -0.56
     Lond
    -0.56
    POSITIVE LOGITS
     kasarigan
    0.90
     purpoſe
    0.90
     myſelf
    0.88
     pleaſure
    0.86
    حياتها
    0.85
     uſ
    0.82
     Theſe
    0.82
    الحياه
    0.77
     Majefty
    0.77
     itſelf
    0.76
    Act Density 0.992%

    No Known Activations