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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PHONE
    -0.07
     дот
    -0.07
    path
    -0.06
    BOVE
    -0.06
     sedan
    -0.06
    .stamp
    -0.06
     Omar
    -0.06
    paths
    -0.06
     Oscars
    -0.06
    .save
    -0.06
    POSITIVE LOGITS
    奖
    0.08
    (){
↵
    0.07
     народу
    0.06
    <|start_header_id|>
    0.06
     ihre
    0.06
     lawmakers
    0.06
    isoner
    0.06
     ihren
    0.06
    .*;
↵
    0.06
     southeastern
    0.06
    Act Density 0.042%

    No Known Activations