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

    Neuronpedia

    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     восстанов
    -0.06
    指导
    -0.06
    재
    -0.06
    緊
    -0.06
     втра
    -0.06
    	connection
    -0.06
    ancybox
    -0.06
     otp
    -0.06
    走
    -0.06
     №
    -0.06
    POSITIVE LOGITS
    ::.
    0.07
    .warning
    0.07
    ír
    0.07
     ecc
    0.07
    ges
    0.06
    ��이지
    0.06
    верд
    0.06
    ěr
    0.06
    othermal
    0.06
     adorned
    0.06
    Act Density 0.005%

    No Known Activations