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

    Neuronpedia

    INDEX
    Explanations

    references to UI element positioning and offset values

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

    offset

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    txtName
    -0.53
     nôtre
    -0.51
     vœ
    -0.48
     bricolaje
    -0.48
    idamente
    -0.47
     montanha
    -0.47
     czarna
    -0.45
     miniaturka
    -0.45
     transfieras
    -0.44
     vostri
    -0.44
    POSITIVE LOGITS
    offset
    3.00
     offset
    2.78
     Offset
    2.28
    Offset
    2.14
     offsets
    2.03
     OFFSET
    2.02
    OFFSET
    1.84
    offsets
    1.55
    偏移
    1.27
    Offsets
    1.24
    Act Density 0.005%

    No Known Activations