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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (;
    -0.08
     Nancy
    -0.07
    .deleteById
    -0.07
    *p
    -0.07
    catid
    -0.07
    =./
    -0.07
    �
    -0.07
    &&!
    -0.07
     Nil
    -0.07
    鲻
    -0.07
    POSITIVE LOGITS
     Portuguese
    0.08
    支柱
    0.07
    ighbours
    0.07
    け
    0.07
    	    ↵
    0.07
    ped
    0.07
     tâm
    0.06
     יש
    0.06
    告
    0.06
    党委书记
    0.06
    Act Density 0.203%

    No Known Activations