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

    Neuronpedia

    INDEX
    Explanations

    few

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bt
    -0.08
     upside
    -0.08
    gt
    -0.07
     year
    -0.07
     Pacific
    -0.07
     Allen
    -0.07
    Pacific
    -0.07
    localhost
    -0.07
     Austria
    -0.06
     ได
    -0.06
    POSITIVE LOGITS
     spp
    0.07
     관련
    0.06
    (hw
    0.06
    ��
    0.06
     Bravo
    0.06
     vhod
    0.06
    лоп
    0.06
    IBE
    0.06
    vala
    0.06
    .MIN
    0.06
    Act Density 0.021%

    No Known Activations