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

    Neuronpedia

    INDEX
    Explanations

    thesis requests and outlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    theta
    0.83
    t
    0.81
    taste
    0.78
     quiescent
    0.76
    ിലാ
    0.75
    𝑡
    0.75
    як
    0.73
    tic
    0.73
    td
    0.73
    tı
    0.72
    POSITIVE LOGITS
    aurus
    0.95
     defense
    0.94
    惫
    0.92
    ulfate
    0.87
     defence
    0.86
    บค
    0.86
     backbone
    0.85
    us
    0.85
    есть
    0.84
     сервера
    0.84
    Act Density 0.003%

    No Known Activations