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

    Neuronpedia

    INDEX
    Explanations

    function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.82
     and
    0.67
    :
    0.65
     (
    0.62
    不
    0.61
    ,
    0.60
     in
    0.59
    D
    0.58
     и
    0.58
     D
    0.58
    POSITIVE LOGITS
    <unused2135>
    0.83
    ⏮
    0.74
    🕣
    0.72
    🕤
    0.72
     Unión
    0.72
     subprocess
    0.71
     atriz
    0.71
    🚱
    0.71
     اولمپس
    0.71
    जुर्ग
    0.70
    Act Density 1.792%

    No Known Activations