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

    Neuronpedia

    INDEX
    Explanations

    specific version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    throws
    1.12
    ቂያ
    1.08
    꿀
    1.06
    пет
    1.01
     Вер
    0.99
     الدراسي
    0.99
    SPORT
    0.99
    Mn
    0.98
     verticals
    0.98
    ίες
    0.95
    POSITIVE LOGITS
    ーリー
    1.25
     tagline
    1.16
     inviting
    1.15
     taka
    1.07
     distinct
    1.05
     activist
    1.03
     awareness
    1.00
     म्हण
    0.99
     देखकर
    0.99
     longing
    0.98
    Act Density 0.000%

    No Known Activations