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

    Neuronpedia

    INDEX
    Explanations

    code and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uters
    -0.07
    _cust
    -0.07
    継
    -0.07
     /*#__
    -0.06
    /story
    -0.06
    之间
    -0.06
    anghai
    -0.06
    [,]
    -0.06
    提
    -0.06
    _workspace
    -0.06
    POSITIVE LOGITS
    arrow
    0.07
    ектив
    0.06
     dropped
    0.06
     treatment
    0.06
     protr
    0.06
    (layer
    0.06
    .Text
    0.06
     questo
    0.06
     Dun
    0.06
    Treatment
    0.06
    Act Density 1.820%

    No Known Activations