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

    Neuronpedia

    INDEX
    Explanations

    weight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mutation
    -0.07
     Python
    -0.07
    ara
    -0.07
     Latin
    -0.06
     Emma
    -0.06
    _STRUCTURE
    -0.06
    Emma
    -0.06
     proof
    -0.06
     Github
    -0.06
     Homer
    -0.06
    POSITIVE LOGITS
    ेखत
    0.06
    woff
    0.06
    ";
↵
    0.06
     Aless
    0.06
     тоб
    0.06
     �
    0.06
    _URI
    0.06
     venues
    0.06
    ACL
    0.06
    升
    0.06
    Act Density 0.006%

    No Known Activations