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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conclusions or final assessments

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

    concluding or drawing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.51
     noqa
    -0.49
     localObject
    -0.49
    unehmen
    -0.47
    WaitGroup
    -0.47
    IntoConstraints
    -0.47
     acoper
    -0.44
    tableFuture
    -0.44
     surla
    -0.44
     looted
    -0.44
    POSITIVE LOGITS
    Geplaatst
    0.43
    開
    0.40
    يكب
    0.39
    Issue
    0.39
     construct
    0.38
    Construct
    0.37
    issue
    0.35
    OrCreate
    0.35
     issue
    0.35
     Construct
    0.35
    Act Density 0.131%

    No Known Activations