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

    Neuronpedia

    INDEX
    Explanations

    news reporting and official statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yaitu
    0.64
     which
    0.61
     которую
    0.57
     который
    0.54
     которая
    0.54
    which
    0.52
     Which
    0.50
     которое
    0.48
     причем
    0.47
     vilket
    0.47
    POSITIVE LOGITS
     newspaper
    0.55
     blog
    0.50
     газета
    0.47
     newspapers
    0.47
    報導
    0.46
     journal
    0.46
     blogger
    0.46
    他說
    0.46
     Huffington
    0.46
     CNBC
    0.45
    Act Density 0.011%

    No Known Activations