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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    feed
    -0.07
    Sell
    -0.07
     ner
    -0.06
    outs
    -0.06
     Audi
    -0.06
     особист
    -0.06
     Sales
    -0.06
    presence
    -0.06
     upro
    -0.06
    紀
    -0.06
    POSITIVE LOGITS
     GOODS
    0.07
     TValue
    0.07
     �
    0.07
    .Ε
    0.06
    ANTITY
    0.06
    RELATED
    0.06
    egin
    0.06
     Lorem
    0.06
     $_[
    0.06
    <Void
    0.06
    Act Density 0.016%

    No Known Activations