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

    Neuronpedia

    INDEX
    Explanations

    mark twain or finds its

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     determinate
    0.47
     аб
    0.46
     кіль
    0.46
     абстра
    0.46
     financiers
    0.45
     рее
    0.42
     unital
    0.42
     кому
    0.42
     exchangers
    0.41
     наук
    0.41
    POSITIVE LOGITS
    visit
    0.47
     Fallen
    0.47
     b
    0.45
     Bite
    0.45
    L
    0.44
     Visit
    0.43
     Bu
    0.43
    ح
    0.43
    nes
    0.42
    The
    0.42
    Act Density 0.006%

    No Known Activations