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

    Neuronpedia

    INDEX
    Explanations

    historical names and significant numeric values

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

    coordinates and chemical notations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Diweddarwch
    -0.51
     betweenstory
    -0.48
    -------
    -0.45
    inSlope
    -0.44
    esgue
    -0.42
    ArrowToggle
    -0.42
    ecap
    -0.41
    AddTagHelper
    -0.40
     ivelany
    -0.39
     utafitiHapana
    -0.39
    POSITIVE LOGITS
    ftagPool
    0.58
     Rukh
    0.46
    たた
    0.43
     candidates
    0.42
     výbě
    0.41
     recherchez
    0.41
    Samstag
    0.40
     Racing
    0.40
     Candidates
    0.40
    JoinTable
    0.40
    Act Density 0.671%

    No Known Activations