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

    Neuronpedia

    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     address
    -0.07
     sustaining
    -0.07
     mover
    -0.07
    .Graphics
    -0.06
     Zodiac
    -0.06
    strike
    -0.06
    盒
    -0.06
     Những
    -0.06
    �
    -0.06
    Bucket
    -0.06
    POSITIVE LOGITS
    ')↵
    0.08
     lear
    0.07
    .setVerticalGroup
    0.07
    ）↵
    0.07
    REFERRED
    0.06
     |
↵
    0.06
     milan
    0.06
    !')↵
    0.06
    _Session
    0.06
    ี้↵
    0.06
    Act Density 0.089%

    No Known Activations