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

    Neuronpedia

    INDEX
    Explanations

    legal/government texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    福
    -0.08
    🍅
    -0.08
     martin
    -0.07
    鸢
    -0.07
    深度融合
    -0.07
    ≻
    -0.07
    uestas
    -0.07
     ><
    -0.07
    ��
    -0.07
    えば
    -0.06
    POSITIVE LOGITS
     quiet
    0.08
    雌
    0.07
    cząc
    0.07
     Play
    0.06
     tấm
    0.06
    촤
    0.06
    搴
    0.06
    yard
    0.06
    Procedure
    0.06
    现身
    0.06
    Act Density 0.010%

    No Known Activations