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

    Neuronpedia

    INDEX
    Explanations

    talking to or heat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bechyné
    0.39
    उदा
    0.35
    บน
    0.31
     सिफारिश
    0.31
     अधिकतम
    0.31
     देशा
    0.31
     elution
    0.31
    <unused82>
    0.31
    र्दू
    0.30
    SXml
    0.30
    POSITIVE LOGITS
     and
    0.39
    ’
    0.36
     or
    0.35
    [
    0.34
    ↵
    0.34
     If
    0.34
    ).
    0.33
     [
    0.33
    .
    0.33
    В
    0.33
    Act Density 0.001%

    No Known Activations