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

    Neuronpedia

    INDEX
    Explanations

    It is/was/shall be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⼒
    0.46
     whopping
    0.42
     Chartered
    0.42
    ATIONAL
    0.41
    כּ
    0.41
    mazon
    0.41
     groundbreaking
    0.41
     dal
    0.40
    ショナル
    0.40
     גם
    0.40
    POSITIVE LOGITS
     scarcely
    0.49
     would
    0.44
     seldom
    0.42
     surely
    0.40
     appeared
    0.40
    Surely
    0.40
     вовсе
    0.39
     hardly
    0.38
     chiefly
    0.38
     starred
    0.38
    Act Density 0.002%

    No Known Activations