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

    Neuronpedia

    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    culus
    -0.07
     لح
    -0.06
     Stanley
    -0.06
     كن
    -0.06
     ncols
    -0.06
    cky
    -0.06
     Cable
    -0.06
     paul
    -0.06
    _checkout
    -0.06
    IDA
    -0.06
    POSITIVE LOGITS
     timestamps
    0.07
    ]};↵
    0.07
     roku
    0.06
    Allows
    0.06
     kys
    0.06
    >::
    0.06
    ög
    0.06
    Metrics
    0.06
    riday
    0.06
     эф
    0.06
    Act Density 0.038%

    No Known Activations