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

    Neuronpedia

    INDEX
    Explanations

    fresh start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    战斗
    0.51
    SA
    0.48
     drill
    0.47
    办公
    0.46
     قصير
    0.45
     بني
    0.44
    奈
    0.44
    Cheat
    0.43
    公式
    0.42
     nectar
    0.42
    POSITIVE LOGITS
    um
    0.61
    ک
    0.55
    ut
    0.53
    andes
    0.53
     Andes
    0.53
    urusan
    0.51
    ام
    0.50
     Andreev
    0.50
     Messrs
    0.49
     ತೋರಿಸ
    0.49
    Act Density 0.001%

    No Known Activations