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

    Neuronpedia

    INDEX
    Explanations

    dump

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Công
    -0.07
    -0.07
    婵
    -0.07
     {:.
    -0.07
    훈
    -0.07
    不行
    -0.07
    电线
    -0.07
     Nonetheless
    -0.07
     Alive
    -0.07
     Publisher
    -0.07
    POSITIVE LOGITS
     dump
    0.10
     dumped
    0.08
    צפי
    0.07
    לוט
    0.07
     Adoption
    0.07
    祃
    0.07
    jom
    0.07
    鲬
    0.07
    _dual
    0.07
    뮴
    0.07
    Act Density 0.005%

    No Known Activations