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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causation or the act of making something happen

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

    what makes / made / constitutes / binds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tampoco
    -0.41
     GoogleFonts
    -0.40
     dép
    -0.37
     inertia
    -0.37
     getItemCount
    -0.35
    ollett
    -0.35
     однако
    -0.34
     nakalista
    -0.34
     dazu
    -0.33
    şört
    -0.33
    POSITIVE LOGITS
     why
    0.60
    Why
    0.58
     Why
    0.57
     waarom
    0.56
    Cechy
    0.55
    why
    0.54
     varför
    0.54
     męski
    0.52
     osobow
    0.52
    руктура
    0.51
    Act Density 0.010%

    No Known Activations