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

    Neuronpedia

    INDEX
    Explanations

    words related to utility and functionality in a context of recommendations

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

    instructions and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     orejas
    -0.42
     Tiefen
    -0.40
     république
    -0.39
     Stamm
    -0.38
     Ruhe
    -0.37
     risa
    -0.37
     vergüenza
    -0.35
     estrada
    -0.35
     stessi
    -0.35
     Rollen
    -0.35
    POSITIVE LOGITS
     الرياضيه
    0.96
     queſta
    0.89
     noDo
    0.86
     незавершена
    0.84
    Tembelea
    0.81
     NSCoder
    0.79
     '\\;'
    0.74
     estekak
    0.74
    tagHelperRunner
    0.74
    httphttps
    0.70
    Act Density 0.015%

    No Known Activations