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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	headers
    -0.07
     placer
    -0.06
    است
    -0.06
    -0.06
    -0.06
    ите
    -0.06
    -0.06
    �
    -0.06
    											↵
    -0.06
    pliers
    -0.06
    POSITIVE LOGITS
    _MSB
    0.07
     انجمن
    0.07
    -led
    0.07
    CESS
    0.07
    copy
    0.06
    .kotlin
    0.06
     getWidth
    0.06
    evaluate
    0.06
    .clear
    0.06
    _Act
    0.06
    Act Density 0.054%

    No Known Activations