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

    Neuronpedia

    INDEX
    Explanations

    plainly

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dmg
    -0.07
     zh
    -0.07
    isty
    -0.07
    xmm
    -0.07
    	mem
    -0.07
    e
    -0.06
    ło
    -0.06
    bit
    -0.06
    	ft
    -0.06
    ǽ
    -0.06
    POSITIVE LOGITS
                    
↵
    0.07
     CNC
    0.07
     Peanut
    0.07
    确定
    0.07
    煤炭
    0.07
    就有了
    0.07
    인데
    0.06
     healing
    0.06
    手工
    0.06
    涵盖了
    0.06
    Act Density 0.001%

    No Known Activations