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

    Neuronpedia

    INDEX
    Explanations

    marginal likelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    day
    0.56
     day
    0.52
     swelling
    0.50
    ci
    0.48
     soap
    0.48
    lerden
    0.48
    days
    0.46
    hler
    0.46
     to
    0.46
    lerin
    0.46
    POSITIVE LOGITS
    ิด
    0.62
     πριν
    0.58
    ید
    0.57
    ುತ್ತದೆ
    0.54
     வால்பேப்ப
    0.53
    これは
    0.52
    ]-\
    0.52
    निश्ड
    0.51
    یدر
    0.51
    ㅡ
    0.51
    Act Density 0.000%

    No Known Activations