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

    Neuronpedia

    INDEX
    Explanations

    legal acts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卵
    -0.07
     dẫn
    -0.07
    liğe
    -0.07
    年产
    -0.06
    前沿
    -0.06
     Madd
    -0.06
    笑了笑
    -0.06
     ');↵↵
    -0.06
     الأسهم
    -0.06
    _LEN
    -0.06
    POSITIVE LOGITS
    @hotmail
    0.07
    ‧
    0.07
    (se
    0.06
    选定
    0.06
     Epoch
    0.06
    到处
    0.06
     horn
    0.06
    (for
    0.06
    (Profile
    0.06
    iards
    0.06
    Act Density 0.000%

    No Known Activations