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

    Neuronpedia

    INDEX
    Explanations

    For

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     是
    -0.07
     автом
    -0.07
    🛁
    -0.07
    ted
    -0.07
    .xls
    -0.06
    אוניברסיטת
    -0.06
     Guru
    -0.06
    _gps
    -0.06
     Django
    -0.06
     collaps
    -0.06
    POSITIVE LOGITS
     reliance
    0.07
    ◉
    0.07
    .tokens
    0.07
     optimization
    0.06
     inspiration
    0.06
     bags
    0.06
    荥
    0.06
     provider
    0.06
     opportunity
    0.06
    쉔
    0.06
    Act Density 0.001%

    No Known Activations