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

    Neuronpedia

    INDEX
    Explanations

    freeCodeCamp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inating
    0.43
     zan
    0.43
    ণ্ড
    0.37
    㚣
    0.37
    subkey
    0.37
     sputter
    0.37
     وث
    0.37
     Hunts
    0.37
     hammer
    0.36
     bhan
    0.36
    POSITIVE LOGITS
     alleine
    0.43
     Alone
    0.39
     keempat
    0.39
     कोर्स
    0.39
    บอก
    0.38
     مصروف
    0.38
    만
    0.38
    filesystem
    0.38
     Tells
    0.38
    marker
    0.38
    Act Density 0.002%

    No Known Activations