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

    Neuronpedia

    INDEX
    Explanations

    co

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HeaderInSection
    -0.07
     Tell
    -0.07
    irim
    -0.07
    呓
    -0.06
     vững
    -0.06
    .writeFile
    -0.06
    խ
    -0.06
    石头
    -0.06
    匍
    -0.06
    /cart
    -0.06
    POSITIVE LOGITS
    裁
    0.08
    апр
    0.07
    Texas
    0.07
    括
    0.07
    Anti
    0.07
    Gro
    0.07
    itted
    0.07
    atcher
    0.07
    ocio
    0.07
     addictive
    0.07
    Act Density 0.000%

    No Known Activations