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

    Neuronpedia

    INDEX
    Explanations

    ened

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urre
    -0.07
     compiling
    -0.07
     expulsion
    -0.06
    攻打
    -0.06
    ưng
    -0.06
    砧
    -0.06
     nộp
    -0.06
    ién
    -0.06
    inp
    -0.06
    inging
    -0.06
    POSITIVE LOGITS
     THAT
    0.07
    .BLACK
    0.07
    RESP
    0.07
    brities
    0.07
     QSize
    0.07
     supremacy
    0.07
    的角色
    0.07
    ';↵↵↵↵
    0.07
     השת
    0.07
    迟
    0.07
    Act Density 0.001%

    No Known Activations