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

    Neuronpedia

    INDEX
    Explanations

    Comparisons and quantities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insistence
    -0.06
     educator
    -0.06
     painstaking
    -0.06
     çoğ
    -0.06
    اریخ
    -0.06
     sacrifice
    -0.06
     poi
    -0.06
     Nightmare
    -0.06
    ń
    -0.06
    терес
    -0.06
    POSITIVE LOGITS
     різні
    0.07
     kys
    0.07
    /package
    0.06
    reira
    0.06
    [])↵
    0.06
    enin
    0.06
     "}";↵
    0.06
     []);↵
    0.06
    韓
    0.06
    abyte
    0.06
    Act Density 0.101%

    No Known Activations