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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe ranges or comparisons between two points or elements

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

    from X to Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     git
    -0.35
    FetchType
    -0.34
     receiver
    -0.33
    GEBURTSDATUM
    -0.32
     convention
    -0.30
     cruc
    -0.30
    mors
    -0.30
     Convention
    -0.30
    ガラ
    -0.30
     transf
    -0.30
    POSITIVE LOGITS
     utafitiHapana
    0.78
     nahilalakip
    0.68
    ranging
    0.57
     ranging
    0.56
    :✨
    0.52
     incluyendo
    0.52
    كويكب
    0.52
    PreferredItem
    0.51
    desde
    0.51
     From
    0.50
    Act Density 0.073%

    No Known Activations