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

    Neuronpedia

    INDEX
    Explanations

    finally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    翼
    -0.07
    משחק
    -0.07
    خوف
    -0.06
     잘못
    -0.06
    �
    -0.06
    撰
    -0.06
     hailed
    -0.06
    不曾
    -0.06
    وصف
    -0.06
     nad
    -0.06
    POSITIVE LOGITS
    _estimate
    0.07
    ительн
    0.07
     остальн
    0.07
    装修公司
    0.07
    icular
    0.07
     Bass
    0.06
    したら
    0.06
    챦
    0.06
    鹚
    0.06
     Orleans
    0.06
    Act Density 0.001%

    No Known Activations