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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating understanding or comprehension of complex information

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

    "According to" or "as far as I can"

    np_acts-logits-general · gemini-2.0-flash

    according to or as far as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contextLoads
    -0.72
    latego
    -0.68
    principalTable
    -0.67
     Vikipedi
    -0.64
    kfree
    -0.60
    chyma
    -0.60
     Autres
    -0.57
     חיצוניים
    -0.57
     Inscrivez
    -0.56
    apimachinery
    -0.56
    POSITIVE LOGITS
     ACCORD
    0.61
    Según
    0.57
    EDEFAULT
    0.56
    according
    0.55
    Selon
    0.53
     According
    0.51
     Menurut
    0.50
    According
    0.50
     according
    0.50
     según
    0.49
    Act Density 0.215%

    No Known Activations