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

    Neuronpedia

    INDEX
    Explanations

    tweets and mentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     growing
    0.70
     molding
    0.70
     growth
    0.69
     fiduciary
    0.67
     niche
    0.66
     cookware
    0.66
     grow
    0.64
     warfare
    0.64
     sublimation
    0.63
     moldings
    0.62
    POSITIVE LOGITS
     @
    2.78
     (@
    2.72
     `@
    2.36
     tweeted
    2.27
     tweets
    2.26
    (@
    2.26
     @_
    2.20
     tweet
    2.17
     '@
    2.16
     "@
    2.16
    Act Density 0.169%

    No Known Activations