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

    Neuronpedia

    INDEX
    Explanations

    court appearances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     grooming
    -0.07
    Matthew
    -0.07
    روز
    -0.07
    哲
    -0.07
     ol
    -0.06
     kul
    -0.06
     regimes
    -0.06
    daki
    -0.06
     Fiesta
    -0.06
     saver
    -0.06
    POSITIVE LOGITS
    _Click
    0.07
     Legislative
    0.07
    .Criteria
    0.06
    ovalo
    0.06
     crossword
    0.06
    (opcode
    0.06
    ][
    0.06
     encompass
    0.06
     предус
    0.06
     Ω
    0.06
    Act Density 0.025%

    No Known Activations