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

    Neuronpedia

    INDEX
    Explanations

    Statistics and measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocument
    -0.08
    𖤐
    -0.07
    侃
    -0.07
    💿
    -0.07
    狳
    -0.07
     GetData
    -0.07
    ildenafil
    -0.07
     Watson
    -0.07
    嗒
    -0.06
    嘬
    -0.06
    POSITIVE LOGITS
     Composite
    0.07
    Anti
    0.07
    Messages
    0.07
    後來
    0.07
    	idx
    0.07
    !?
    0.07
    公
    0.07
    HOST
    0.07
     threads
    0.07
    ถ
    0.06
    Act Density 0.210%

    No Known Activations