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

    Neuronpedia

    INDEX
    Explanations

    reviewer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cod
    -0.07
    Fragment
    -0.07
     gesture
    -0.07
    (products
    -0.07
    	The
    -0.07
    晚
    -0.07
     satisfying
    -0.07
    依法
    -0.06
    atisf
    -0.06
    ثل
    -0.06
    POSITIVE LOGITS
    続いて
    0.07
    metatable
    0.07
    /pkg
    0.07
    emat
    0.07
    حوال
    0.07
    เผย
    0.07
    쉈
    0.07
    独一
    0.07
     libertin
    0.07
    直通车
    0.06
    Act Density 0.003%

    No Known Activations