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

    Neuronpedia

    INDEX
    Explanations

    code and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المق
    -0.08
    	index
    -0.07
    袋
    -0.06
     placed
    -0.06
     cuts
    -0.06
     vulnerable
    -0.06
     opioid
    -0.06
     quasi
    -0.06
     radios
    -0.06
    .related
    -0.06
    POSITIVE LOGITS
     Choosing
    0.07
     Cannot
    0.07
     sexuales
    0.07
    назнач
    0.06
     birisi
    0.06
    <?>>
    0.06
     Far
    0.06
    >d
    0.06
    .Lookup
    0.06
    .getColumn
    0.06
    Act Density 0.016%

    No Known Activations