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

    Neuronpedia

    INDEX
    Explanations

    plt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τικα
    -0.07
    บค
    -0.07
     getline
    -0.07
     Stafford
    -0.07
     accompagn
    -0.06
    ฤษภาคม
    -0.06
     Vườn
    -0.06
    .fr
    -0.06
    ário
    -0.06
    ollapsed
    -0.06
    POSITIVE LOGITS
     فار
    0.07
     жел
    0.07
    Thinking
    0.06
    Vol
    0.06
    Ten
    0.06
     соответ
    0.06
     renting
    0.06
     Residence
    0.06
     esteemed
    0.06
     Voll
    0.06
    Act Density 0.013%

    No Known Activations