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

    Neuronpedia

    INDEX
    Explanations

    Code and math functions

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    uestion
    -0.08
    פופול
    -0.07
    uate
    -0.07
     Prescription
    -0.07
    GetInstance
    -0.07
     songs
    -0.07
     enterprises
    -0.06
    ISON
    -0.06
    _big
    -0.06
    越野
    -0.06
    POSITIVE LOGITS
    技术和
    0.07
     acceso
    0.07
    .Metadata
    0.07
    砘
    0.07
    有大量的
    0.07
    .Typed
    0.07
    عدل
    0.07
     fps
    0.07
    =$((
    0.06
    oload
    0.06
    Act Density 0.035%

    No Known Activations