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

    Neuronpedia

    INDEX
    Explanations

    directional terms and route descriptions

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

    north and south directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enderror
    -0.35
     sanction
    -0.34
     Lichten
    -0.33
     Nigerian
    -0.33
    WON
    -0.33
     instrument
    -0.32
     SIT
    -0.30
     '}
    -0.30
    stackSize
    -0.30
     &
    -0.30
    POSITIVE LOGITS
     eastward
    0.81
     southward
    0.81
    MLLoader
    0.78
     westward
    0.75
     downwards
    0.75
     northward
    0.74
     autorytatywna
    0.72
     downward
    0.70
     ujednoznacz
    0.68
     GenerationType
    0.61
    Act Density 0.020%

    No Known Activations