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

    Neuronpedia

    INDEX
    Explanations

    gherkin Feature Scenario or Background

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inom
    0.36
    grupo
    0.36
     prog
    0.35
    ProxyAgent
    0.35
    0.35
     ale
    0.34
     ->
    0.34
     burl
    0.34
    hern
    0.33
    ():
    0.33
    POSITIVE LOGITS
     Background
    0.62
     Feature
    0.59
     BACKGROUND
    0.59
    Background
    0.57
     feature
    0.56
    Feature
    0.56
     background
    0.55
     Lettuce
    0.55
     Cucumber
    0.54
     FEATURE
    0.53
    Act Density 0.007%

    No Known Activations