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

    Neuronpedia

    INDEX
    Explanations

    .org

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inhabit
    -0.07
    总结
    -0.07
    奠基
    -0.07
    นา
    -0.07
    抓好
    -0.07
     hour
    -0.07
    促
    -0.07
     Disable
    -0.06
    菟
    -0.06
     enhance
    -0.06
    POSITIVE LOGITS
    sons
    0.07
    險
    0.07
    _sales
    0.07
    _AMOUNT
    0.06
    สมาคม
    0.06
    rganization
    0.06
     bronze
    0.06
    もの
    0.06
    leh
    0.06
    磉
    0.06
    Act Density 0.000%

    No Known Activations