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

    Neuronpedia

    INDEX
    Explanations

    compound

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     퍼
    -0.07
    .picture
    -0.07
    _GATE
    -0.07
     feminism
    -0.07
    高
    -0.06
    _pulse
    -0.06
    erek
    -0.06
    Dave
    -0.06
     дослідження
    -0.06
    isté
    -0.06
    POSITIVE LOGITS
     flags
    0.07
     viewModel
    0.06
     Alman
    0.06
     Products
    0.06
     antid
    0.06
    md
    0.06
     Seed
    0.06
    issue
    0.06
    .multiply
    0.06
    .isArray
    0.06
    Act Density 0.019%

    No Known Activations