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

    Neuronpedia

    INDEX
    Explanations

    disputes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ровод
    -0.07
    .effects
    -0.06
     Wis
    -0.06
     poco
    -0.06
    _MM
    -0.06
    IDEOS
    -0.06
    _representation
    -0.06
     시작
    -0.06
    .LOGIN
    -0.06
    	parameters
    -0.06
    POSITIVE LOGITS
    ，没有
    0.07
     삶
    0.07
     آلة
    0.07
    quests
    0.06
    하였다
    0.06
     искус
    0.06
     Мар
    0.06
    .Must
    0.06
     �
    0.06
     Petersburg
    0.06
    Act Density 0.016%

    No Known Activations