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

    Neuronpedia

    INDEX
    Explanations

    geographical features and locations

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

    Cardinal directions

    np_acts-logits-general · gemini-2.0-flash

    cardinal directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transfer
    -1.26
     Transfer
    -1.07
    Transfer
    -1.01
    transfer
    -1.01
     transferencia
    -0.95
     transferring
    -0.95
     transferred
    -0.94
     transfers
    -0.91
     TRANSFER
    -0.88
     transfert
    -0.84
    POSITIVE LOGITS
     north
    1.32
     south
    1.31
     east
    1.23
     west
    1.21
     southward
    1.06
    north
    1.05
     eastward
    1.01
     southbound
    1.00
     northward
    1.00
     southwest
    1.00
    Act Density 0.129%

    No Known Activations