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

    Neuronpedia

    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     offic
    -0.07
    odies
    -0.06
     Previously
    -0.06
     Blackjack
    -0.06
     surviv
    -0.06
     incre
    -0.06
     bon
    -0.06
     cott
    -0.06
     traps
    -0.06
     ride
    -0.06
    POSITIVE LOGITS
     sqlSession
    0.07
    Dll
    0.07
    ครอง
    0.07
     كه
    0.07
     öff
    0.07
     Poh
    0.07
    (iParam
    0.06
     Fucked
    0.06
    cpp
    0.06
     полити
    0.06
    Act Density 0.017%

    No Known Activations