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

    Neuronpedia

    INDEX
    Explanations

    emojis and expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PROXY
    0.42
    ETT
    0.39
    IVERSITY
    0.39
    SWITCH
    0.38
    UNICATIONS
    0.38
    BATCH
    0.38
    JUNE
    0.38
     গ্রন্থ
    0.37
    SHUNT
    0.37
    DARK
    0.37
    POSITIVE LOGITS
     smiling
    0.57
     emoji
    0.56
     smiley
    0.51
     Emoji
    0.50
     sourire
    0.50
     улы
    0.49
     smile
    0.48
     grinning
    0.46
     emojis
    0.46
     smirk
    0.46
    Act Density 0.054%

    No Known Activations