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

    Neuronpedia

    INDEX
    Explanations

    T cells

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     endforeach
    -0.08
    ">{{$
    -0.07
     Metodo
    -0.07
     Massive
    -0.07
     них
    -0.07
    ===
    -0.07
    =models
    -0.07
     además
    -0.07
     months
    -0.07
     único
    -0.07
    POSITIVE LOGITS
    .external
    0.07
     inert
    0.06
    जन
    0.06
    ูง
    0.06
     teb
    0.06
    deriv
    0.06
     اون
    0.06
    ilim
    0.06
     excit
    0.06
     розви
    0.06
    Act Density 0.031%

    No Known Activations