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

    Neuronpedia

    INDEX
    Explanations

    presenting options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ussie
    0.48
     seal
    0.48
     produk
    0.47
     aviso
    0.47
     بي
    0.47
     marque
    0.46
    ustral
    0.46
    odhpur
    0.46
     service
    0.46
    OC
    0.46
    POSITIVE LOGITS
    目标
    0.52
    📉
    0.51
    ============
    0.51
    🧠
    0.51
     -----------
    0.49
    情绪
    0.48
     BlueprintName
    0.47
    🤯
    0.47
    ================
    0.47
    给定
    0.46
    Act Density 0.010%

    No Known Activations