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

    Neuronpedia

    INDEX
    Explanations

    object key "name"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    公益
    0.65
     There
    0.57
    られます
    0.56
     Besides
    0.54
     Expedition
    0.54
     Podcast
    0.53
     March
    0.53
     meteorite
    0.52
     Kickstarter
    0.52
    丰富的
    0.52
    POSITIVE LOGITS
    斫
    0.54
    ᱘
    0.53
     dividers
    0.52
    ܗ
    0.52
    )}=\
    0.51
    enstein
    0.51
    geri
    0.51
    elves
    0.50
    אים
    0.50
    )},\
    0.49
    Act Density 0.001%

    No Known Activations