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

    Neuronpedia

    INDEX
    Explanations

    math proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kỳ
    -0.07
    挈
    -0.07
    毓
    -0.07
    ��
    -0.06
     Ré
    -0.06
    arer
    -0.06
    蝰
    -0.06
     JB
    -0.06
    bilder
    -0.06
    表
    -0.06
    POSITIVE LOGITS
     photons
    0.08
    .Unit
    0.07
     misconduct
    0.07
    -icons
    0.07
     creat
    0.07
    实务
    0.07
     negligence
    0.07
    航行
    0.07
     puzzles
    0.07
    .responseText
    0.07
    Act Density 0.015%

    No Known Activations