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

    Neuronpedia

    INDEX
    Explanations

    words that indicate significant influence or importance

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

    influential roles and subjects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <>",
    -0.65
     صفحۀ
    -0.59
    SOUNDBITE
    -0.56
    Liefs
    -0.56
    Groet
    -0.54
     vVar
    -0.53
     gynhyrchwyd
    -0.53
    yelitis
    -0.52
    رایط
    -0.51
    RRect
    -0.51
    POSITIVE LOGITS
     influential
    1.78
     Influ
    0.98
    influ
    0.90
     influ
    0.86
    Influ
    0.84
     prominent
    0.77
     impactful
    0.73
     powerful
    0.69
     INFLU
    0.68
     influencers
    0.68
    Act Density 0.007%

    No Known Activations