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

    Neuronpedia

    INDEX
    Explanations

    In

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     управ
    -0.07
     overwrite
    -0.07
    рит
    -0.07
    Skip
    -0.07
    :Event
    -0.06
     users
    -0.06
    ریک
    -0.06
     Workers
    -0.06
     critic
    -0.06
     workers
    -0.06
    POSITIVE LOGITS
    lene
    0.07
    )*/↵
    0.06
     fla
    0.06
    лач
    0.06
    .Protocol
    0.06
    SPATH
    0.06
    /a
    0.06
     representations
    0.06
                        ↵
    0.06
    σσ
    0.06
    Act Density 0.038%

    No Known Activations