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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    센터
    -0.07
     historically
    -0.07
    DEX
    -0.06
    Builder
    -0.06
    Ack
    -0.06
    .ValidationError
    -0.06
    Chunk
    -0.06
     gef
    -0.06
    	Create
    -0.06
    ��
    -0.06
    POSITIVE LOGITS
    ute
    0.07
    .memo
    0.07
    _scheme
    0.06
     specifically
    0.06
    )];↵
    0.06
     instructions
    0.06
     diligent
    0.06
    icí
    0.06
     utilis
    0.06
    tolist
    0.06
    Act Density 0.063%

    No Known Activations