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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avoids
    -0.07
     Québec
    -0.07
     descri
    -0.07
     brut
    -0.06
     waiter
    -0.06
     PCs
    -0.06
    лені
    -0.06
    dej
    -0.06
    ��
    -0.06
    地下
    -0.06
    POSITIVE LOGITS
    (messages
    0.07
    {x
    0.07
     ActionController
    0.06
    	delay
    0.06
     supplies
    0.06
     attendee
    0.06
    multiline
    0.06
     باشگاه
    0.06
    .DataBindings
    0.06
     '\'
    0.06
    Act Density 0.001%

    No Known Activations