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

    Neuronpedia

    INDEX
    Explanations

    Negative comparisons and sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    añ
    -0.07
    28
    -0.06
    irc
    -0.06
     meaningful
    -0.06
     bluff
    -0.06
     bonds
    -0.06
     Bonds
    -0.06
     Kum
    -0.06
    apture
    -0.06
     jump
    -0.06
    POSITIVE LOGITS
     newPosition
    0.07
     граду
    0.06
     ltd
    0.06
     teenager
    0.06
     $('#'
    0.06
    Arn
    0.06
    -be
    0.06
    주소
    0.06
    (attr
    0.06
    _CONN
    0.06
    Act Density 0.033%

    No Known Activations