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

    Neuronpedia

    INDEX
    Explanations

    weight loss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pomoć
    -0.07
     inspiration
    -0.07
    Observers
    -0.07
    Funny
    -0.07
     ček
    -0.07
    Nodes
    -0.07
     observation
    -0.07
     actor
    -0.07
    Actors
    -0.07
     volatility
    -0.07
    POSITIVE LOGITS
     তা
    0.09
     সত
    0.08
     puas
    0.08
    -inch
    0.08
     Schip
    0.08
     compromet
    0.07
     hunger
    0.07
     withdrawing
    0.07
    wget
    0.07
     nourishing
    0.07
    Act Density 0.008%

    No Known Activations