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

    Neuronpedia

    INDEX
    Explanations

    relative pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Certain
    -0.07
    _net
    -0.07
     Pressure
    -0.07
    Certain
    -0.07
     concurrently
    -0.07
     Andrea
    -0.07
     warmly
    -0.06
     heavily
    -0.06
     (?
    -0.06
     "'
    -0.06
    POSITIVE LOGITS
    .Property
    0.07
     äl
    0.07
    psilon
    0.06
     cJSON
    0.06
     punched
    0.06
    습니다
    0.06
    Gen
    0.06
     snag
    0.06
    _SEPARATOR
    0.06
    tiği
    0.06
    Act Density 0.070%

    No Known Activations