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

    Neuronpedia

    INDEX
    Explanations

    Country codes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .CONTENT
    -0.07
     culmination
    -0.07
    Bounding
    -0.07
    ㉡
    -0.07
    CrLf
    -0.07
     armored
    -0.07
    理解
    -0.07
    三分
    -0.06
     Carol
    -0.06
     FOUND
    -0.06
    POSITIVE LOGITS
     UK
    0.07
    台
    0.07
    껨
    0.07
    שער
    0.07
    /components
    0.06
     problematic
    0.06
     medios
    0.06
     European
    0.06
    ている
    0.06
    菖
    0.06
    Act Density 0.002%

    No Known Activations