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

    Neuronpedia

    INDEX
    Explanations

    Grove

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    东亚
    -0.07
    哚
    -0.07
    _tok
    -0.07
    	cerr
    -0.07
     социально
    -0.07
    Occ
    -0.07
    批发市场
    -0.06
    دافع
    -0.06
    Amt
    -0.06
    黜
    -0.06
    POSITIVE LOGITS
     MACHINE
    0.08
    =Y
    0.07
     building
    0.07
    גיע
    0.07
     greeting
    0.07
     בגל
    0.07
     posible
    0.07
    .GetEnumerator
    0.06
     grup
    0.06
    紋
    0.06
    Act Density 0.001%

    No Known Activations