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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쩡
    -0.07
    /backend
    -0.07
    垒
    -0.07
    email
    -0.06
    脈
    -0.06
    	email
    -0.06
    斗
    -0.06
    敬
    -0.06
    �
    -0.06
    香
    -0.06
    POSITIVE LOGITS
     VIP
    0.07
    财报
    0.07
    ичество
    0.07
     Chronicles
    0.07
     commuters
    0.07
     Hours
    0.07
     tyr
    0.06
    序幕
    0.06
    mapping
    0.06
     upwards
    0.06
    Act Density 0.001%

    No Known Activations