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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    守
    -0.08
     출시
    -0.08
     Released
    -0.08
    released
    -0.08
    整体
    -0.08
    chá
    -0.07
     محس
    -0.07
    reise
    -0.07
    ถือ
    -0.07
    言
    -0.07
    POSITIVE LOGITS
     מקום
    0.13
     جگہ
    0.12
     જગ
    0.11
     место
    0.11
     spaces
    0.11
     площад
    0.11
     공간
    0.11
     designated
    0.11
     ruimte
    0.11
    _placeholder
    0.11
    Act Density 0.007%

    No Known Activations