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

    Neuronpedia

    INDEX
    Explanations

    commas and "and"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Switch
    -0.06
    Coll
    -0.06
    ComboBox
    -0.06
     kissing
    -0.06
     Efficient
    -0.06
    ays
    -0.06
    _sign
    -0.06
     Leak
    -0.06
     مدیر
    -0.06
     SNAP
    -0.06
    POSITIVE LOGITS
    ANTLR
    0.07
     ┃
    0.07
    ipment
    0.07
    667
    0.07
     recommended
    0.07
     porr
    0.06
     limitation
    0.06
     جنسی
    0.06
     Commentary
    0.06
     труд
    0.06
    Act Density 0.095%

    No Known Activations