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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Roll
    -0.07
    Victoria
    -0.07
    Aaron
    -0.07
    TK
    -0.07
     ger
    -0.07
    Alexander
    -0.07
    KS
    -0.06
     ke
    -0.06
     ken
    -0.06
    education
    -0.06
    POSITIVE LOGITS
     прожива
    0.08
    stoi
    0.08
    agenta
    0.07
     заяв
    0.07
    区域内
    0.07
     spriteBatch
    0.07
     canopy
    0.07
    名列前
    0.07
    stadt
    0.07
     بحي
    0.07
    Act Density 0.017%

    No Known Activations