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

    Neuronpedia

    INDEX
    Explanations

    choices involving risks and consequences

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

    choices and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maj
    -0.43
     major
    -0.40
     too
    -0.39
    prefixer
    -0.39
     si
    -0.38
     til
    -0.38
    zell
    -0.38
    identi
    -0.38
     often
    -0.37
    link
    -0.37
    POSITIVE LOGITS
    httphttps
    0.66
     Chwiliwch
    0.64
     defaultstate
    0.64
    ChildScrollView
    0.63
    ReusableCell
    0.62
    رشف
    0.61
     miniaturka
    0.60
    EndContext
    0.59
    WriteTagHelper
    0.59
     Geſch
    0.58
    Act Density 0.047%

    No Known Activations