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

    Neuronpedia

    INDEX
    Explanations

    depend

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lines
    -0.07
     Hilton
    -0.07
    inning
    -0.07
    -Y
    -0.07
    -create
    -0.06
     Nicht
    -0.06
     circular
    -0.06
    uarios
    -0.06
     Dallas
    -0.06
    Combat
    -0.06
    POSITIVE LOGITS
     мар
    0.07
     erót
    0.06
    ็นผ
    0.06
    :http
    0.06
    ++){
    0.06
     أص
    0.06
     harek
    0.06
     Farage
    0.06
     зах
    0.06
    imageView
    0.06
    Act Density 0.201%

    No Known Activations