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

    Neuronpedia

    INDEX
    Explanations

    😊 after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     notes
    0.83
     Inicio
    0.81
     memoranda
    0.81
     Lets
    0.78
    শিদ
    0.77
     পূর্বে
    0.76
    Notes
    0.75
    Let
    0.75
     Notes
    0.75
     Yates
    0.74
    POSITIVE LOGITS
     😉
    1.95
     ;)
    1.81
     ;-)
    1.75
     😂
    1.73
     :)
    1.57
    😜
    1.56
     😄
    1.55
     haha
    1.54
     :-)
    1.53
     hahaha
    1.52
    Act Density 0.326%

    No Known Activations