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

    Neuronpedia

    INDEX
    Explanations

    references and citations related to academic or formal texts

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

    numbers and specific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fjspx
    -0.75
    rawDesc
    -0.68
    ArrowToggle
    -0.67
    IVEREF
    -0.66
    setVerticalGroup
    -0.66
    ScopeManager
    -0.65
     nakalista
    -0.64
    featureID
    -0.61
    AndEndTag
    -0.57
    KommentareTeilen
    -0.57
    POSITIVE LOGITS
     piernas
    0.36
     nueces
    0.35
     events
    0.33
    extré
    0.33
     Weeks
    0.32
     Year
    0.32
     memory
    0.31
    ajemen
    0.31
    ĩa
    0.31
    真实的
    0.30
    Act Density 0.033%

    No Known Activations