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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Drinks
    -0.06
     Kramer
    -0.06
    Moving
    -0.06
     Мед
    -0.06
     Woche
    -0.06
     Inspector
    -0.06
    .cost
    -0.06
    Talking
    -0.06
    cks
    -0.06
    ,",
    -0.06
    POSITIVE LOGITS
    akhir
    0.07
    pios
    0.06
    preserve
    0.06
    ('\
    0.06
     dojo
    0.06
    >{@
    0.06
    ({
↵
    0.06
     dollar
    0.06
    coon
    0.06
    lator
    0.06
    Act Density 0.142%

    No Known Activations