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

    Neuronpedia

    INDEX
    Explanations

    AI conversational elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чком
    0.58
    чек
    0.47
    ονται
    0.46
    eyim
    0.46
    putable
    0.44
    pers
    0.43
     capped
    0.43
    terus
    0.42
    撳
    0.41
    班
    0.41
    POSITIVE LOGITS
     upgrades
    0.46
    สำหรับ
    0.46
     MTN
    0.46
     INCRE
    0.45
     NEM
    0.45
    ূল
    0.45
     aggress
    0.44
     agress
    0.43
     giving
    0.43
     wasting
    0.43
    Act Density 0.001%

    No Known Activations