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

    Neuronpedia

    INDEX
    Explanations

    depends on context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    值
    0.44
    ircraft
    0.44
    听
    0.44
     weak
    0.43
     clonal
    0.43
     metade
    0.42
     undetected
    0.42
     anest
    0.42
    ᱗
    0.40
     undocumented
    0.40
    POSITIVE LOGITS
    Markdown
    0.47
    Html
    0.47
    1
    0.46
    CO
    0.46
    App
    0.45
    Table
    0.44
    \</
    0.44
    Thing
    0.44
    Data
    0.43
    HTML
    0.43
    Act Density 0.220%

    No Known Activations