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

    Neuronpedia

    INDEX
    Explanations

    technical components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eer
    -0.07
     induce
    -0.07
     cite
    -0.06
    CR
    -0.06
     Become
    -0.06
    Texto
    -0.06
    ition
    -0.06
    	x
    -0.06
    enson
    -0.06
     SX
    -0.06
    POSITIVE LOGITS
    tit
    0.07
     กร
    0.07
     Кан
    0.06
     قهر
    0.06
    했고
    0.06
    	rc
    0.06
    Dirs
    0.06
     ldc
    0.06
     keyValue
    0.06
     mnoho
    0.06
    Act Density 0.034%

    No Known Activations