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

    Neuronpedia

    INDEX
    Explanations

    children

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     독일
    -0.07
     هدف
    -0.07
    یستم
    -0.07
     普
    -0.06
     مت
    -0.06
    controls
    -0.06
     
↵
↵
    -0.06
    ovaly
    -0.06
    .Download
    -0.06
    анс
    -0.06
    POSITIVE LOGITS
     v
    0.07
    Â
    0.07
    qr
    0.06
     stuffed
    0.06
    _diag
    0.06
     جع
    0.06
    СР
    0.06
     intrig
    0.06
    occo
    0.06
     ModelRenderer
    0.06
    Act Density 0.130%

    No Known Activations