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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software configuration and UI elements

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

    Code, programming, or configuration attributes

    np_acts-logits-general · gemini-2.0-flash

    UI controls and data display

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     
    -0.53
     old
    -0.51
     sin
    -0.49
     of
    -0.43
     long
    -0.43
    ๆ
    -0.43
     τέ
    -0.42
     s
    -0.42
    !
    -0.41
     d
    -0.40
    POSITIVE LOGITS
     resourceCulture
    1.10
    DockStyle
    1.09
    rungsseite
    1.06
    :✨
    1.00
    +#+#
    1.00
     Exactos
    0.98
     pinulongan
    0.97
    EDEFAULT
    0.96
    CloseOperation
    0.94
    GEBURTSDATUM
    0.89
    Act Density 0.543%

    No Known Activations