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

    Neuronpedia

    INDEX
    Explanations

    URL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     amnesty
    -0.07
     bicy
    -0.07
     asserted
    -0.07
    냨
    -0.07
    /o
    -0.07
    _filters
    -0.06
    荃
    -0.06
    一开始
    -0.06
    \<^
    -0.06
    卤
    -0.06
    POSITIVE LOGITS
    ㈭
    0.07
    0.07
    应当
    0.06
    �
    0.06
    :↵↵↵↵↵↵
    0.06
    ﳕ
    0.06
     необходимо
    0.06
    当今
    0.06
     Additionally
    0.06
    要及时
    0.06
    Act Density 0.000%

    No Known Activations