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

    Neuronpedia

    INDEX
    Explanations

    monadic bind and map operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Бар
    0.42
     Leighton
    0.40
     жи
    0.39
     пище
    0.39
     Lyric
    0.38
     жид
    0.38
    enderita
    0.37
    TGFuZ
    0.37
     เฉล
    0.37
     الذ
    0.37
    POSITIVE LOGITS
     map
    0.85
    map
    0.82
    flatMap
    0.78
     flat
    0.70
     lift
    0.62
    Map
    0.61
     Map
    0.60
    zip
    0.59
     zip
    0.57
     mapped
    0.56
    Act Density 0.007%

    No Known Activations