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

    Neuronpedia

    INDEX
    Explanations

    html attributes: id, class, onclick, alt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    adığı
    0.29
    ማ
    0.27
    UTES
    0.26
    gever
    0.26
    ETTE
    0.26
    gä
    0.26
     सामु
    0.25
    glich
    0.25
    NaF
    0.25
    meno
    0.25
    POSITIVE LOGITS
     >
    0.38
     class
    0.35
    >(
    0.34
     id
    0.33
     ><
    0.33
    ><
    0.32
     %>
    0.30
     );
    0.30
     ></
    0.29
    }>
    0.29
    Act Density 0.004%

    No Known Activations