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

    Neuronpedia

    INDEX
    Explanations

    ami, lama, origami, llama

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ए
    0.80
    َس
    0.73
    َ
    0.73
    टीशन
    0.73
    因为
    0.72
    含む
    0.70
    示した
    0.70
    τή
    0.69
    看到
    0.68
    の大
    0.68
    POSITIVE LOGITS
    the
    0.78
    I
    0.73
    br
    0.71
     can
    0.70
     Afghans
    0.68
    ni
    0.68
    s
    0.68
    ns
    0.67
    nas
    0.67
     Pelicans
    0.66
    Act Density 0.003%

    No Known Activations