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

    Neuronpedia

    INDEX
    Explanations

    extends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ',)↵
    -0.06
    /bind
    -0.06
     sudoku
    -0.06
     mike
    -0.06
    یدا
    -0.06
     kuru
    -0.06
     Neville
    -0.06
    cter
    -0.06
     ediyor
    -0.06
     whisper
    -0.06
    POSITIVE LOGITS
    .That
    0.07
    _locations
    0.07
    Coroutine
    0.07
    _HOT
    0.07
     fasting
    0.07
     act
    0.07
    px
    0.06
     exc
    0.06
    tot
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations