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

    Neuronpedia

    INDEX
    Explanations

    code and URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    락
    -0.07
     Yard
    -0.07
    went
    -0.07
    Nullable
    -0.06
    _HINT
    -0.06
     substituted
    -0.06
    SORT
    -0.06
    _FUNCTIONS
    -0.06
    _REGS
    -0.06
    Board
    -0.06
    POSITIVE LOGITS
     Benn
    0.06
     xe
    0.06
    еся
    0.06
    zahl
    0.06
    -Jan
    0.06
    ^K
    0.06
     GETGLOBAL
    0.06
    straint
    0.06
     Moz
    0.06
    ylül
    0.06
    Act Density 0.261%

    No Known Activations