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

    Neuronpedia

    INDEX
    Explanations

    needs something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    star
    0.51
    water
    0.50
    therapy
    0.49
    ogast
    0.48
    wine
    0.47
     W
    0.47
     Medications
    0.47
     Wisconsin
    0.46
    wick
    0.45
    thorn
    0.45
    POSITIVE LOGITS
    یم
    0.49
    نګه
    0.48
     بسیاری
    0.46
     گراف
    0.46
    یر
    0.46
     درباره
    0.46
     konuş
    0.45
     منفی
    0.43
    क्षित
    0.43
     بانک
    0.43
    Act Density 0.012%

    No Known Activations