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

    Neuronpedia

    INDEX
    Explanations

    gamma radiation and distribution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.05
    jär
    0.99
    iling
    0.97
    ED
    0.97
    an
    0.95
     are
    0.94
    io
    0.93
     arousal
    0.92
    érique
    0.91
    आर
    0.89
    POSITIVE LOGITS
    家
    1.26
    Z
    1.13
    ี
    1.11
    来
    1.09
    رك
    1.07
     gamma
    1.05
    半
    1.05
    脸
    1.04
    Gamma
    1.01
    رس
    1.01
    Act Density 0.004%

    No Known Activations