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

    Neuronpedia

    INDEX
    Explanations

    be or may

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    像是
    -0.08
    SEMB
    -0.07
     emphasize
    -0.07
     elabor
    -0.07
     creams
    -0.06
    一致
    -0.06
     dee
    -0.06
     запрос
    -0.06
     secret
    -0.06
     AL
    -0.06
    POSITIVE LOGITS
     stringByAppendingString
    0.08
    客户
    0.08
    🔭
    0.08
    外形
    0.07
    展馆
    0.07
     wound
    0.07
    ⵟ
    0.07
    变速箱
    0.07
    },{↵
    0.07
     bump
    0.07
    Act Density 0.022%

    No Known Activations