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

    Neuronpedia

    INDEX
    Explanations

    unpublished data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    毫升
    -0.08
    넛
    -0.07
     drowned
    -0.07
    魅
    -0.07
    мент
    -0.06
     ned
    -0.06
    might
    -0.06
     pierced
    -0.06
    уществ
    -0.06
    艺人
    -0.06
    POSITIVE LOGITS
     Assessment
    0.08
     Santa
    0.07
    .*↵
    0.07
     עסקי
    0.07
     resolving
    0.07
    -state
    0.07
     слишком
    0.07
     Balance
    0.07
     SC
    0.07
    ورو
    0.06
    Act Density 0.049%

    No Known Activations