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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate demonstration or explanation

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

    purpose of showing/demonstrating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jScrollPane
    -0.63
     Chwiliwch
    -0.61
     useRouter
    -0.57
     Normdatei
    -0.57
    ScopeManager
    -0.56
    SequentialGroup
    -0.54
    səhifə
    -0.54
    MigrationBuilder
    -0.54
    الحياه
    -0.54
    AnchorStyles
    -0.54
    POSITIVE LOGITS
     showing
    0.57
     montrer
    0.55
    Showing
    0.54
     Showing
    0.54
    showing
    0.51
     montrant
    0.50
    show
    0.47
     mostrar
    0.46
    Show
    0.45
     Show
    0.44
    Act Density 0.042%

    No Known Activations