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

    Neuronpedia

    INDEX
    Explanations

    language modelhigh blood pressurenamed entityWorld Heritage siteDepartment of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rong
    -0.09
    xdb
    -0.09
    /cop
    -0.08
    ÏĩεδÏĮν
    -0.08
     УкÑĢаÑĹ
    -0.08
    OUNDS
    -0.08
    HttpException
    -0.08
    åĢij
    -0.07
    etty
    -0.07
    ¯
    -0.07
    POSITIVE LOGITS
    led
    0.09
    ledge
    0.09
    ed
    0.08
    lege
    0.08
    letters
    0.08
    ably
    0.08
    hazi
    0.08
    quat
    0.08
    OfDay
    0.08
    pace
    0.08
    Act Density 0.004%

    No Known Activations