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

    Neuronpedia

    INDEX
    Explanations

    combust

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    222
    -0.07
    gy
    -0.07
    54
    -0.07
     stripes
    -0.06
     *)↵
    -0.06
    Door
    -0.06
     inquiries
    -0.06
     swing
    -0.06
    234
    -0.06
     duro
    -0.06
    POSITIVE LOGITS
     छ
    0.07
     Breast
    0.07
     Burns
    0.06
    .wind
    0.06
    GetType
    0.06
    checkBox
    0.06
     يا
    0.06
     шп
    0.06
    过去
    0.06
    ΕΧ
    0.06
    Act Density 0.001%

    No Known Activations