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

    Neuronpedia

    INDEX
    Explanations

    common words and terms related to scientific research and methodologies

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

    conditional dependence between variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.57
     AssemblyCompany
    -0.53
    Πηγές
    -0.52
    Hochspringen
    -0.47
    󠁢
    -0.46
    istoitu
    -0.46
    ниципа
    -0.42
    extAlignment
    -0.41
     MainAxisSize
    -0.41
     magnético
    -0.40
    POSITIVE LOGITS
    tanleria
    0.51
    хьтан
    0.44
    setopt
    0.43
     enfans
    0.42
    новниш
    0.41
     ſind
    0.41
     TType
    0.40
    ⟬
    0.39
    ſelf
    0.39
     draught
    0.39
    Act Density 0.001%

    No Known Activations