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

    Neuronpedia

    INDEX
    Explanations

    hyphens parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Exit
    -0.07
    isnan
    -0.07
     Ary
    -0.06
     derivatives
    -0.06
     hid
    -0.06
    Amy
    -0.06
     perpetrator
    -0.06
    	DWORD
    -0.06
    先生
    -0.06
     Dong
    -0.06
    POSITIVE LOGITS
    čním
    0.07
    /*!
    0.07
    /article
    0.07
     ℝ
    0.07
    _internal
    0.06
    lients
    0.06
     painters
    0.06
    croft
    0.06
    _air
    0.06
    (msg
    0.06
    Act Density 0.023%

    No Known Activations