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

    Neuronpedia

    INDEX
    Explanations

    code, math, and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ListOf
    -0.08
     것을
    -0.07
     "***
    -0.07
     아이
    -0.07
    He
    -0.07
     suche
    -0.07
     Dense
    -0.07
    中に
    -0.07
     argued
    -0.07
    овах
    -0.06
    POSITIVE LOGITS
     incumb
    0.06
     SNMP
    0.06
     TAS
    0.06
    ()));
    0.06
     insurers
    0.06
    S
    0.06
    agon
    0.06
     substr
    0.06
     };
    0.06
     sdk
    0.06
    Act Density 0.012%

    No Known Activations