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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tube
    -0.06
     ミ
    -0.06
    acam
    -0.06
     �
    -0.06
    λού
    -0.06
    ,item
    -0.06
     seizure
    -0.06
    retch
    -0.06
     té
    -0.06
     الاقتص
    -0.06
    POSITIVE LOGITS
     instructions
    0.10
     directions
    0.07
    USAGE
    0.07
     sunglasses
    0.07
     rules
    0.07
    .Bitmap
    0.07
     instructed
    0.06
     direction
    0.06
     regulations
    0.06
    Instructions
    0.06
    Act Density 0.036%

    No Known Activations