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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ap
    -0.08
    aj
    -0.07
    _ac
    -0.07
    ücret
    -0.07
    leyen
    -0.07
    -F
    -0.07
     Без
    -0.07
     en
    -0.07
    оза
    -0.07
    -port
    -0.07
    POSITIVE LOGITS
     honeymoon
    0.07
    <?>>
    0.06
    .Cmd
    0.06
     Democratic
    0.06
    proposal
    0.06
    альную
    0.06
     Async
    0.06
     Incontri
    0.06
    .setHorizontalGroup
    0.06
     MMA
    0.06
    Act Density 0.073%

    No Known Activations