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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tess
    -0.07
    ילד
    -0.07
    Parm
    -0.07
    젛
    -0.07
    五大
    -0.07
     пят
    -0.07
     thoughtful
    -0.07
    롹
    -0.07
    낏
    -0.07
     Carp
    -0.07
    POSITIVE LOGITS
    .creator
    0.07
    ogs
    0.07
    uploads
    0.07
    .activation
    0.07
    朋友们对
    0.07
     postfix
    0.07
    댜
    0.07
    Opacity
    0.06
    চ
    0.06
    צטר
    0.06
    Act Density 0.001%

    No Known Activations