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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lok
    -0.06
    Indent
    -0.06
     preced
    -0.06
    ayet
    -0.06
    κτή
    -0.06
     Separate
    -0.06
     kd
    -0.06
     locker
    -0.06
    _Init
    -0.06
    ाइ
    -0.06
    POSITIVE LOGITS
    ：↵↵
    0.07
     ребенок
    0.07
    Personally
    0.06
    υ
    0.06
    :url
    0.06
    [dir
    0.06
    permalink
    0.06
    े
    0.06
     stability
    0.06
    紙
    0.06
    Act Density 0.011%

    No Known Activations