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

    Neuronpedia

    INDEX
    Explanations

    function and command definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .-(
    0.43
     playroom
    0.40
    蟎
    0.40
     ભાગ
    0.40
     রেখেছে
    0.39
    戽
    0.38
    న్న
    0.38
     MINISTRY
    0.38
    ائش
    0.37
    Rets
    0.37
    POSITIVE LOGITS
    {\
    0.70
     ${\
    0.62
     {"
    0.51
    *{\
    0.49
    }{\
    0.48
     {\
    0.46
     {@
    0.46
    {"
    0.45
     }{\
    0.45
    my
    0.44
    Act Density 0.001%

    No Known Activations