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

    Neuronpedia

    INDEX
    Explanations

    Medical abbreviations/references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ительной
    -0.07
    grass
    -0.07
    ิโน
    -0.06
     disdain
    -0.06
     ren
    -0.06
     etm
    -0.06
    .chain
    -0.06
    міні
    -0.06
     reco
    -0.06
     wisdom
    -0.06
    POSITIVE LOGITS
    cta
    0.07
     Contributor
    0.06
    ->
    0.06
    -bl
    0.06
    CU
    0.06
    _sentence
    0.06
    只要
    0.06
    ENV
    0.06
    _FAR
    0.06
    ANC
    0.06
    Act Density 0.050%

    No Known Activations