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

    Neuronpedia

    INDEX
    Explanations

    actions and activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cmd
    -0.07
    第一章
    -0.07
    (("
    -0.07
    periment
    -0.07
     TRADE
    -0.07
     future
    -0.06
    🅓
    -0.06
     Wow
    -0.06
    楼主
    -0.06
     students
    -0.06
    POSITIVE LOGITS
     Lebanese
    0.08
     Hezbollah
    0.08
    PointerType
    0.07
     câ
    0.07
     FontWeight
    0.07
    ኢ
    0.07
    �
    0.07
     הר
    0.07
     Holocaust
    0.07
    								
↵
    0.07
    Act Density 0.521%

    No Known Activations