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

    Neuronpedia

    INDEX
    Explanations

    Interview transcriptions/quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ensures
    -0.07
    �
    -0.07
    ù
    -0.06
    ȍ
    -0.06
    劭
    -0.06
    ┭
    -0.06
     occurs
    -0.06
     JIT
    -0.06
    Codec
    -0.06
    _EMIT
    -0.06
    POSITIVE LOGITS
    	Connection
    0.08
     pix
    0.07
    	Query
    0.07
    _hop
    0.07
     Mund
    0.07
     psychological
    0.07
    砌
    0.07
     prayers
    0.07
    祝
    0.07
    ุง
    0.06
    Act Density 0.110%

    No Known Activations