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

    Neuronpedia

    INDEX
    Explanations

    references to navigation and movement through various routes

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

    movement along a route

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.57
    MessageTagHelper
    -0.55
    awtextra
    -0.54
    KommentareTeilen
    -0.53
    cshtml
    -0.50
    Diwedd
    -0.46
    Personendaten
    -0.46
    :✨
    -0.45
    คัญ
    -0.44
    kenstock
    -0.43
    POSITIVE LOGITS
     passing
    1.35
     via
    1.31
     passando
    1.24
    passing
    1.20
     melewati
    1.18
     passant
    1.13
     passes
    1.10
    via
    1.10
     pasando
    1.10
     Passing
    1.08
    Act Density 0.086%

    No Known Activations