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

    Neuronpedia

    INDEX
    Explanations

    references to positions or rankings in a competitive context

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

    back to speed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.46
     feroit
    -0.44
     civilización
    -0.44
     besky
    -0.42
    ſelves
    -0.42
     sensitivity
    -0.41
     verksamhet
    -0.41
     islands
    -0.40
     underground
    -0.40
     sû
    -0.40
    POSITIVE LOGITS
     propOrder
    0.58
    tagHelperRunner
    0.53
    AnchorStyles
    0.52
     Chwiliwch
    0.50
    inSlope
    0.50
    IntoConstraints
    0.49
     שוליים
    0.49
     "..\..\
    0.48
     "..\..\..\
    0.47
    IsMutable
    0.46
    Act Density 0.011%

    No Known Activations