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

    Neuronpedia

    INDEX
    Explanations

    render template view

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Literal
    0.38
    聸
    0.38
    рово
    0.37
    =\""
    0.37
    rical
    0.36
    bilical
    0.36
    "#
    0.36
     आटे
    0.36
    ]-\
    0.36
     pouce
    0.36
    POSITIVE LOGITS
    layouts
    0.69
     templates
    0.63
     layouts
    0.61
     view
    0.59
     template
    0.55
    视图
    0.53
    テンプレート
    0.52
    view
    0.52
    templates
    0.52
    welcome
    0.50
    Act Density 0.001%

    No Known Activations