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

    Neuronpedia

    INDEX
    Explanations

    industrial and chemical applications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (chip
    -0.07
     overshadow
    -0.06
    (tableName
    -0.06
    found
    -0.06
     grips
    -0.06
    toolStrip
    -0.06
    限制
    -0.06
     CHILD
    -0.06
     Diss
    -0.06
    _BLK
    -0.06
    POSITIVE LOGITS
    BERT
    0.07
     carnival
    0.06
     Dee
    0.06
    .Stop
    0.06
    bert
    0.06
    agged
    0.06
    -В
    0.06
    として
    0.06
    ent
    0.06
    典
    0.06
    Act Density 0.066%

    No Known Activations