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

    Neuronpedia

    INDEX
    Explanations

    grammar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _z
    -0.08
     coatings
    -0.07
     Ко
    -0.07
     Views
    -0.07
     Positive
    -0.06
    _az
    -0.06
     cí
    -0.06
    _OBS
    -0.06
    .MouseDown
    -0.06
     bees
    -0.06
    POSITIVE LOGITS
     manners
    0.07
     grammar
    0.07
     grandmother
    0.06
    那个
    0.06
    ще
    0.06
    /db
    0.06
    맛
    0.06
     procedural
    0.06
     Kendrick
    0.06
    MES
    0.06
    Act Density 0.005%

    No Known Activations