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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ظه
    -0.07
    later
    -0.06
    _tmp
    -0.06
     fullfile
    -0.06
    main
    -0.06
    cretion
    -0.06
    .rl
    -0.06
     justo
    -0.06
     sulf
    -0.06
    ResultSet
    -0.06
    POSITIVE LOGITS
     Controls
    0.07
    ifest
    0.07
    ynes
    0.06
     karış
    0.06
    历
    0.06
    Lastly
    0.06
     війни
    0.06
     MCS
    0.06
     evitar
    0.06
    ุส
    0.06
    Act Density 0.001%

    No Known Activations