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

    Neuronpedia

    INDEX
    Explanations

    references to online sources and platforms related to various topics

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

    Ames test

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     venuto
    -0.43
     AssemblyCompany
    -0.40
    AlterField
    -0.38
     techniczne
    -0.38
     ready
    -0.36
     full
    -0.35
     sk
    -0.35
     disfraces
    -0.35
    Scénario
    -0.35
     hornear
    -0.35
    POSITIVE LOGITS
     الرياضيه
    0.91
    Autoritní
    0.70
    تقاوى
    0.60
    хьтан
    0.59
    ſelves
    0.58
     Италијани
    0.58
    httphttps
    0.56
     ivelany
    0.56
     ་་
    0.55
     ―――――
    0.55
    Act Density 0.002%

    No Known Activations