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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sponge
    -0.07
    imity
    -0.06
    _imm
    -0.06
     нап
    -0.06
     KG
    -0.06
    епти
    -0.06
    .gz
    -0.06
    298
    -0.06
    čen
    -0.06
    Lat
    -0.06
    POSITIVE LOGITS
    (move
    0.07
    tester
    0.06
    ATEST
    0.06
    MF
    0.06
     зали
    0.06
     ~~
    0.06
    winner
    0.06
     errorMessage
    0.06
     pillows
    0.06
    istributed
    0.06
    Act Density 0.001%

    No Known Activations