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

    Neuronpedia

    INDEX
    Explanations

    table headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    轫
    0.43
     ##
    0.41
     \...
    0.39
     Lauf
    0.38
     ـ
    0.38
     />}></
    0.38
    ),\
    0.37
     ⚫
    0.37
    আস
    0.36
    aspid
    0.36
    POSITIVE LOGITS
    */
    0.44
    %=
    0.43
    |=
    0.42
    --;
    0.40
    ---|
    0.40
    -->
    0.40
    &=
    0.40
     CNY
    0.39
    <thead>
    0.39
    --
    0.38
    Act Density 0.092%

    No Known Activations