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

    Neuronpedia

    INDEX
    Explanations

    links to resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تمام
    0.44
     fantasia
    0.42
     Kön
    0.41
     banderas
    0.41
     چیر
    0.41
     Már
    0.41
     zur
    0.41
     alegria
    0.41
     görül
    0.40
     sadece
    0.40
    POSITIVE LOGITS
     nbsp
    0.45
    Consent
    0.44
    ‑
    0.43
    ChatGPT
    0.42
    icrob
    0.42
    फ़
    0.41
    вЂ
    0.41
     FAQs
    0.40
    এ
    0.40
     opioid
    0.40
    Act Density 0.001%

    No Known Activations