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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     His
    -0.08
     his
    -0.08
    เง
    -0.07
     A
    -0.06
     Bellev
    -0.06
    thren
    -0.06
    .devices
    -0.06
     having
    -0.06
     Our
    -0.06
     mixed
    -0.06
    POSITIVE LOGITS
    "];
↵
    0.07
    (ALOAD
    0.07
    ừa
    0.06
    .xlim
    0.06
    ContentLoaded
    0.06
     青
    0.06
     separates
    0.06
    _MSB
    0.06
    '));
↵
    0.06
     fint
    0.06
    Act Density 0.118%

    No Known Activations