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

    Neuronpedia

    INDEX
    Explanations

    mobile

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -he
    -0.08
    集
    -0.07
    辐
    -0.07
    펀
    -0.07
    -wage
    -0.07
     Attend
    -0.07
     aggreg
    -0.07
    -msg
    -0.07
     TMP
    -0.07
    /XML
    -0.07
    POSITIVE LOGITS
     eating
    0.08
     gal
    0.07
    */↵↵
    0.07
    כב
    0.07
    quel
    0.07
    eties
    0.07
     ballet
    0.07
    席卷
    0.07
     contato
    0.06
    	total
    0.06
    Act Density 0.003%

    No Known Activations