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

    Neuronpedia

    INDEX
    Explanations

    notice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jared
    -0.08
    vae
    -0.07
     Adelaide
    -0.07
    虾
    -0.07
    颅
    -0.07
     genetic
    -0.07
    GST
    -0.07
     garden
    -0.06
     Semi
    -0.06
    מלי
    -0.06
    POSITIVE LOGITS
    反正
    0.08
    pery
    0.07
    verständlich
    0.07
    społ
    0.07
    なんと
    0.07
    ropol
    0.07
    ��
    0.07
    циальн
    0.06
     שכן
    0.06
     ;;=
    0.06
    Act Density 0.006%

    No Known Activations