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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (nil
    -0.07
    .serializer
    -0.07
    PELL
    -0.07
    Bundle
    -0.06
    BindingUtil
    -0.06
     погод
    -0.06
    .getDrawable
    -0.06
     Закону
    -0.06
     определен
    -0.06
    .cpu
    -0.06
    POSITIVE LOGITS
     Cow
    0.08
     Ne
    0.07
     Ree
    0.07
     Str
    0.07
     às
    0.06
     Kem
    0.06
     Ke
    0.06
     Se
    0.06
     Fitz
    0.06
     Kee
    0.06
    Act Density 0.254%

    No Known Activations