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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hospitalized
    -0.07
    /stretchr
    -0.07
     escalating
    -0.06
     foram
    -0.06
    Inset
    -0.06
    .ns
    -0.06
    زي
    -0.06
    ленно
    -0.06
     festive
    -0.06
     AFTER
    -0.06
    POSITIVE LOGITS
     Peanut
    0.08
     Sioux
    0.07
    -flag
    0.07
    -out
    0.07
    pur
    0.07
     hf
    0.07
     philosoph
    0.06
    -update
    0.06
    nh
    0.06
    má
    0.06
    Act Density 0.001%

    No Known Activations