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

    Neuronpedia

    INDEX
    Explanations

    file not found or registered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    냐면
    0.39
    𒋾
    0.34
    度和
    0.34
    性和
    0.33
     그러면은
    0.33
    Porque
    0.32
    ]}/
    0.32
     سارے
    0.32
    사가
    0.31
    כּ
    0.31
    POSITIVE LOGITS
    ！
    0.66
    !")
    0.63
    !\
    0.62
    !
    0.60
    !!!
    0.57
    !",
    0.57
     !!!
    0.57
    !!!!
    0.55
     \
    0.55
    !"
    0.55
    Act Density 0.037%

    No Known Activations