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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating approximate quantities or statistical references

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

    approximate numerical values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Houſe
    -0.67
    DockStyle
    -0.60
     estekak
    -0.59
     Italijani
    -0.59
    ########.
    -0.58
    хьтан
    -0.58
    :✨
    -0.57
     propOrder
    -0.56
    SharedCtor
    -0.56
    elemField
    -0.56
    POSITIVE LOGITS
    ximately
    0.47
     approximately
    0.46
    y
    0.45
    mately
    0.39
    ximadamente
    0.39
    IMATE
    0.38
     cromado
    0.38
    览
    0.38
     approximate
    0.37
    ize
    0.36
    Act Density 0.015%

    No Known Activations