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
     HTTPS
    -0.07
     Catalonia
    -0.07
    کش
    -0.06
     ≥
    -0.06
     Aussie
    -0.06
    ecimal
    -0.06
    _bb
    -0.06
     Beitrag
    -0.06
    			↵			↵
    -0.06
     mijn
    -0.06
    POSITIVE LOGITS
     convention
    0.06
     kez
    0.06
    話
    0.06
     карт
    0.06
     popcorn
    0.06
    �
    0.06
    .snp
    0.06
    allowed
    0.06
     위치
    0.06
     Narc
    0.06
    Act Density 0.030%

    No Known Activations