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

    Neuronpedia

    INDEX
    Explanations

    protection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     combination
    -0.07
     suit
    -0.06
     onComplete
    -0.06
    forget
    -0.06
     Lớp
    -0.06
     ldc
    -0.06
     longstanding
    -0.06
     sessuali
    -0.06
    няют
    -0.06
     speed
    -0.06
    POSITIVE LOGITS
    getRoot
    0.06
    Painter
    0.06
     OAuth
    0.06
    >;↵
    0.06
    avirus
    0.06
     damaging
    0.06
    vehicles
    0.06
    coder
    0.06
    iber
    0.06
     Yellowstone
    0.06
    Act Density 0.033%

    No Known Activations