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

    Neuronpedia

    INDEX
    Explanations

    States

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cart
    -0.07
    VEL
    -0.06
     дир
    -0.06
     gå
    -0.06
    바이
    -0.06
    éli
    -0.06
    _height
    -0.06
     hrd
    -0.06
    .’↵↵
    -0.06
    ;">
    -0.06
    POSITIVE LOGITS
    Victoria
    0.07
     famously
    0.07
     Rc
    0.06
     toi
    0.06
     estos
    0.06
    usually
    0.06
    extern
    0.06
    XmlNode
    0.06
     Corona
    0.06
    옥
    0.06
    Act Density 0.020%

    No Known Activations