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

    Neuronpedia

    INDEX
    Explanations

    Code and questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lhs
    -0.07
     برای
    -0.06
     방법
    -0.06
     gebruik
    -0.06
    tam
    -0.06
    	dt
    -0.06
     ساده
    -0.06
    真
    -0.06
    	json
    -0.06
     тка
    -0.06
    POSITIVE LOGITS
    oly
    0.07
    _GEN
    0.06
    �
    0.06
    icipant
    0.06
    zano
    0.06
     conven
    0.06
    χν
    0.06
     Municipal
    0.06
     Bron
    0.06
    Unt
    0.06
    Act Density 0.149%

    No Known Activations