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

    Neuronpedia

    INDEX
    Explanations

    generates JSON or attributes like `"id" = "value"`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，”
    0.38
     circuitry
    0.37
    WebpackPlugin
    0.37
    url
    0.36
     perspective
    0.36
     morphed
    0.36
    ツ
    0.36
    curl
    0.36
    eret
    0.36
     اع
    0.35
    POSITIVE LOGITS
     Scholars
    0.43
    தாய
    0.42
     Needed
    0.41
     STARS
    0.40
     Statement
    0.39
     Statements
    0.39
     तैयारी
    0.38
     follows
    0.38
     Grounds
    0.38
    ifadə
    0.38
    Act Density 0.003%

    No Known Activations