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

    Neuronpedia

    INDEX
    Explanations

    issue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Get
    -0.07
    .config
    -0.07
     undergone
    -0.06
     Accred
    -0.06
    コン
    -0.06
    hide
    -0.06
     occupying
    -0.06
    sWith
    -0.06
    .Group
    -0.06
     Drinks
    -0.06
    POSITIVE LOGITS
    .:.:.:.:
    0.07
    ,:,
    0.07
    >R
    0.07
     όμως
    0.06
     Disqus
    0.06
     rooted
    0.06
    iktig
    0.06
     خود
    0.06
     stochastic
    0.06
    	SDL
    0.06
    Act Density 0.800%

    No Known Activations