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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating causation or explanation

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

    examples and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.35
    bucht
    -0.35
     nigh
    -0.35
    imdi
    -0.35
    ⟭
    -0.34
    хьтан
    -0.34
     waste
    -0.34
    fei
    -0.34
    Lato
    -0.33
    nigh
    -0.33
    POSITIVE LOGITS
    ChildScrollView
    0.56
    Geplaatst
    0.54
    protoimpl
    0.54
    migrationBuilder
    0.53
     AssemblyCompany
    0.53
    GTCX
    0.52
    UpInside
    0.50
    GEBURTSDATUM
    0.50
    TemporalType
    0.50
    +#+#
    0.50
    Act Density 0.126%

    No Known Activations