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

    Neuronpedia

    INDEX
    Explanations

    disagree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Celsius
    -0.07
     gồm
    -0.07
    ----------↵↵
    -0.07
    Expires
    -0.06
     fant
    -0.06
     цел
    -0.06
     capital
    -0.06
    crire
    -0.06
     "*"
    -0.06
    .SetInt
    -0.06
    POSITIVE LOGITS
     disagree
    0.14
     disagreement
    0.13
     disagrees
    0.12
     disagreed
    0.12
     disagreements
    0.12
     startups
    0.07
    Against
    0.07
     contradict
    0.07
    �
    0.06
     meets
    0.06
    Act Density 0.007%

    No Known Activations