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

    Neuronpedia

    INDEX
    Explanations

    references to study results and findings related to research outputs

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

    our research findings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.78
    RenderAtEndOf
    -0.69
     defaultstate
    -0.68
    oredCriteria
    -0.66
    WithIOException
    -0.63
    Personendaten
    -0.62
    RegistryLite
    -0.58
     SwitchCompat
    -0.57
    ftagPool
    -0.55
    IVEREF
    -0.53
    POSITIVE LOGITS
     analysis
    1.13
     analyses
    0.91
     results
    0.90
     análisis
    0.86
    analysis
    0.86
     investigations
    0.84
     investigation
    0.82
     examination
    0.81
     result
    0.77
     hasil
    0.73
    Act Density 0.265%

    No Known Activations