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

    Neuronpedia

    INDEX
    Explanations

    visual icons and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🤣🤣
    0.45
    😂😂
    0.42
    😝
    0.40
    嗄
    0.39
    IGAN
    0.38
    Voids
    0.38
    Winters
    0.38
    😽
    0.38
    ospels
    0.37
     spanned
    0.37
    POSITIVE LOGITS
     magnifying
    0.70
     arrow
    0.68
    globe
    0.68
     arrows
    0.66
     microscope
    0.65
     globe
    0.65
    箭头
    0.65
     briefcase
    0.62
    arrow
    0.61
     icon
    0.61
    Act Density 0.013%

    No Known Activations