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

    Neuronpedia

    INDEX
    Explanations

    conversational snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itre
    -0.07
    ^[
    -0.06
     Sin
    -0.06
     Hue
    -0.06
     هزار
    -0.06
     Charity
    -0.06
     Criteria
    -0.06
     pea
    -0.06
     Zhao
    -0.06
     fazla
    -0.06
    POSITIVE LOGITS
    .setBorder
    0.07
    ив
    0.06
     """↵
    0.06
    ’ya
    0.06
     cannot
    0.06
     viewpoints
    0.06
    hand
    0.06
    Help
    0.06
     должна
    0.06
    权
    0.06
    Act Density 0.036%

    No Known Activations