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

    Neuronpedia

    INDEX
    Explanations

    emojis representing events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.98
     ’’
    0.87
     ï
    0.83
     Ã
    0.81
     =,
    0.81
     ‘’
    0.80
    0.78
    ĭ
    0.77
     \,
    0.76
    0.75
    POSITIVE LOGITS
    <0xF0>
    0.96
    🚀
    0.92
    🌙
    0.89
    🎶
    0.87
    🎄
    0.87
    🎵
    0.87
    😂
    0.86
    🎂
    0.85
    🌎
    0.84
    🌍
    0.84
    Act Density 0.000%

    No Known Activations