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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "ke" in various contexts

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

    directional prepositions and prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     HasFactory
    -0.56
     endblock
    -0.53
     contextLoads
    -0.50
    pmatrix
    -0.50
     enfans
    -0.48
     isEnabled
    -0.47
    Österreich
    -0.47
     ويكيپيديا
    -0.47
     onlyOwner
    -0.47
    ortium
    -0.47
    POSITIVE LOGITS
     ke
    0.91
     into
    0.68
     To
    0.65
     to
    0.65
     naar
    0.64
     toward
    0.64
     προς
    0.62
     onto
    0.61
     towards
    0.60
     hacia
    0.60
    Act Density 0.001%

    No Known Activations