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

    Neuronpedia

    INDEX
    Explanations

    code or legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     float
    -0.06
    aştır
    -0.06
    opyright
    -0.06
    checksum
    -0.06
     диаг
    -0.06
    <String
    -0.06
    istring
    -0.06
     Principles
    -0.06
     无
    -0.06
    Listener
    -0.06
    POSITIVE LOGITS
    >N
    0.07
     IDD
    0.07
    áz
    0.07
    olem
    0.07
    partition
    0.06
     CCC
    0.06
    itled
    0.06
    >E
    0.06
     특히
    0.06
     newsp
    0.06
    Act Density 0.001%

    No Known Activations