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

    Neuronpedia

    INDEX
    Explanations

    made

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tud
    0.81
    Мен
    0.76
     வடி
    0.75
     editing
    0.74
    She
    0.71
     deity
    0.71
    Testing
    0.69
     ergonomics
    0.69
    Editing
    0.69
    God
    0.68
    POSITIVE LOGITS
    ดี
    0.75
    énés
    0.75
     مذہ
    0.70
    ㎡
    0.70
    ına
    0.70
     Partly
    0.70
    touchstart
    0.66
     Hotspur
    0.65
    ınızı
    0.64
    ibc
    0.64
    Act Density 0.001%

    No Known Activations