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
     departments
    -0.06
    initialized
    -0.06
    egral
    -0.06
    стро
    -0.06
    лами
    -0.06
    Claims
    -0.06
    ’↵
    -0.06
    rema
    -0.06
    єн
    -0.06
    lector
    -0.06
    POSITIVE LOGITS
     unbelievable
    0.07
    .keyCode
    0.07
     yeniden
    0.07
     HELP
    0.06
     електрон
    0.06
     YELLOW
    0.06
    .CSS
    0.06
    DF
    0.06
    (++
    0.06
    .Results
    0.06
    Act Density 0.009%

    No Known Activations