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
    _R
    -0.08
     Bereich
    -0.06
    _tE
    -0.06
     상대
    -0.06
     plán
    -0.06
     करन
    -0.06
    ッグ
    -0.06
    �
    -0.06
    رفته
    -0.06
    ')}}">
    -0.06
    POSITIVE LOGITS
    erts
    0.07
    _birth
    0.07
     sout
    0.07
     birthdays
    0.06
     waits
    0.06
     physicians
    0.06
    five
    0.06
     اسم
    0.06
     sugars
    0.06
     outcome
    0.06
    Act Density 0.001%

    No Known Activations