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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    450
    -0.07
     no
    -0.07
     IllegalStateException
    -0.07
     Tradable
    -0.07
     hist
    -0.06
     �
    -0.06
    endid
    -0.06
    placed
    -0.06
    liğine
    -0.06
     liability
    -0.06
    POSITIVE LOGITS
     Pussy
    0.07
    mmc
    0.06
     strs
    0.06
    jpeg
    0.06
    奶
    0.06
     pizzas
    0.06
    [root
    0.06
    /xhtml
    0.06
    morph
    0.06
    UNCTION
    0.06
    Act Density 0.090%

    No Known Activations