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

    Neuronpedia

    INDEX
    Explanations

    if (

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ();
    0.47
     бывают
    0.38
    function
    0.36
     >
    0.36
    かどうか
    0.36
    entropy
    0.36
     >>
    0.35
    aduras
    0.35
    ()['
    0.35
    subtype
    0.35
    POSITIVE LOGITS
     did
    0.89
    did
    0.74
     does
    0.69
     (!
    0.67
     do
    0.64
     Did
    0.61
    Did
    0.61
     ){
    0.58
    <unused2154>
    0.57
    "){
    0.57
    Act Density 0.021%

    No Known Activations