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

    Neuronpedia

    INDEX
    Explanations

    the + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    리카
    0.53
    Có
    0.52
    तो
    0.51
     таки
    0.48
     Cómo
    0.48
    Ско
    0.47
    ;
    0.46
    复制代码
    0.45
    Tìm
    0.45
    Liz
    0.45
    POSITIVE LOGITS
    oretically
    0.63
     propellers
    0.62
    orems
    0.58
     propeller
    0.58
     sediments
    0.55
    atres
    0.54
    ological
    0.53
    atrical
    0.52
     sunsets
    0.52
     incense
    0.51
    Act Density 0.012%

    No Known Activations