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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stime
    -0.08
    _xyz
    -0.08
    ptoms
    -0.07
    »↵↵
    -0.07
     familial
    -0.07
    Interested
    -0.06
     userService
    -0.06
    殁
    -0.06
     hosts
    -0.06
     Curriculum
    -0.06
    POSITIVE LOGITS
    _sphere
    0.07
    第二
    0.07
    oga
    0.07
    的样子
    0.06
    état
    0.06
    ,,
    0.06
     AUT
    0.06
    ☧
    0.06
     최근
    0.06
    先进
    0.06
    Act Density 0.003%

    No Known Activations