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

    Neuronpedia

    INDEX
    Explanations

    elements related to mathematical notation or references

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

    non English mathematical notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GRAPH
    -0.49
     magasiner
    -0.45
    Knife
    -0.44
     Knife
    -0.43
     Mystery
    -0.43
     屋根
    -0.43
    DockStyle
    -0.42
     graphi
    -0.42
     PLAT
    -0.42
    -0.42
    POSITIVE LOGITS
     <>",
    0.49
     gynhyrchwyd
    0.47
     verzorg
    0.45
    ApiOperation
    0.44
    hasMoreElements
    0.41
     Italijani
    0.41
     verwacht
    0.40
     Мексичка
    0.40
    endphp
    0.39
     entanto
    0.38
    Act Density 0.009%

    No Known Activations