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

    Neuronpedia

    INDEX
    Explanations

    /extensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    报酬
    -0.07
    �
    -0.07
    Placeholder
    -0.07
    泞
    -0.07
     ts
    -0.07
     thirsty
    -0.07
     Gloria
    -0.07
     ó
    -0.07
    疼
    -0.06
    чис
    -0.06
    POSITIVE LOGITS
     LAN
    0.08
    emails
    0.07
    altung
    0.07
     ComboBox
    0.07
    尴尬
    0.07
    竟然
    0.07
    	URL
    0.07
    erde
    0.07
    _notice
    0.07
     estar
    0.07
    Act Density 0.005%

    No Known Activations