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

    Neuronpedia

    INDEX
    Explanations

    technical parameters and data types in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical or programming-related expressions

    np_acts-logits-general · gemini-2.0-flash

    linear followed by ]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    badlogic
    -0.59
    ↵↵
    -0.48
     in
    -0.47
     b
    -0.47
     who
    -0.46
     /\.(
    -0.46
    tagHelperRunner
    -0.42
     er
    -0.42
    NgModule
    -0.42
    ţie
    -0.42
    POSITIVE LOGITS
     الحره
    0.84
     समीक्षक
    0.76
     Baillargeon
    0.72
    LabelTagHelper
    0.68
     ModelExpression
    0.67
    ynb
    0.61
     geslacht
    0.60
     EconPapers
    0.59
    ukone
    0.59
     $|
    0.59
    Act Density 0.054%

    No Known Activations