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

    Neuronpedia

    INDEX
    Explanations

    Internet content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的方向
    -0.07
    UPPORT
    -0.07
    ’re
    -0.07
     Were
    -0.06
     מחיר
    -0.06
     measure
    -0.06
    Back
    -0.06
    uary
    -0.06
     touchdown
    -0.06
    喉
    -0.06
    POSITIVE LOGITS
     kleinen
    0.08
    매
    0.08
    .addAll
    0.07
     coleg
    0.07
     mijn
    0.07
    /{}/
    0.07
     blij
    0.07
    詳
    0.07
     Clothing
    0.07
    휼
    0.07
    Act Density 0.052%

    No Known Activations