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

    Neuronpedia

    INDEX
    Explanations

    measurement or specification details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ques
    0.42
    kiej
    0.38
     Senator
    0.38
     नारा
    0.36
    arra
    0.36
     Borden
    0.36
    ristmas
    0.36
     nitrous
    0.36
    йын
    0.35
    ituary
    0.35
    POSITIVE LOGITS
     okol
    0.38
     transfert
    0.38
    Recommendations
    0.38
     üretim
    0.38
     tiktok
    0.37
    Translated
    0.37
     covers
    0.37
     aftermarket
    0.37
    Internal
    0.37
    Subscribe
    0.36
    Act Density 0.000%

    No Known Activations