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

    Neuronpedia

    INDEX
    Explanations

    words that denote disruption or significant impact

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

    comparative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorStyles
    -0.89
    DockStyle
    -0.86
    expandindo
    -0.78
     utafitiHapana
    -0.77
     الرياضيه
    -0.69
    awtextra
    -0.69
     виправивши
    -0.69
    ьаж
    -0.68
     estekak
    -0.66
    ValueStyle
    -0.65
    POSITIVE LOGITS
     brightest
    0.38
     cutest
    0.38
     fonde
    0.38
    imaginary
    0.35
     Kamin
    0.35
     greener
    0.34
     laid
    0.34
     sweetest
    0.32
     Memory
    0.32
     grand
    0.32
    Act Density 0.166%

    No Known Activations