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

    Neuronpedia

    INDEX
    Explanations

    margin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     partager
    -0.08
    .getConnection
    -0.07
     Herman
    -0.07
    .news
    -0.07
    ikit
    -0.07
    twitter
    -0.07
     oportun
    -0.07
    嘻嘻
    -0.07
    .predicate
    -0.07
    /ip
    -0.07
    POSITIVE LOGITS
     stripping
    0.07
    进展
    0.07
    Ending
    0.06
    Mod
    0.06
    Tumblr
    0.06
    adc
    0.06
     folding
    0.06
    -fe
    0.06
    Quantity
    0.06
    oused
    0.06
    Act Density 0.003%

    No Known Activations