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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations or institutions related to military operations

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

    foothills, foothold, footnote

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     París
    -0.45
    Egypte
    -0.40
     incó
    -0.40
     Egipto
    -0.39
     Rusia
    -0.39
     casó
    -0.39
    worm
    -0.38
    욱
    -0.38
     shark
    -0.38
     Rússia
    -0.38
    POSITIVE LOGITS
     foothills
    1.71
     Footh
    1.55
     footh
    1.23
     Piedmont
    1.13
    eway
    0.81
    Pied
    0.79
    pied
    0.74
     pied
    0.68
     foothold
    0.66
     Pied
    0.64
    Act Density 0.006%

    No Known Activations