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

    Neuronpedia

    INDEX
    Explanations

    references to articles and papers in a scholarly context

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

    Following a verb of discussion or analysis

    np_acts-logits-general · gemini-2.0-flash

    future explanation verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ddelweddau
    -0.75
    bootstrapcdn
    -0.72
    منابع
    -0.71
     resourceCulture
    -0.70
    ReusableCell
    -0.70
    Obrázky
    -0.70
     Portail
    -0.69
    astify
    -0.69
     Numerade
    -0.69
     habet
    -0.66
    POSITIVE LOGITS
     examine
    1.16
     discuss
    1.16
     explore
    1.14
     examines
    1.12
     explores
    1.10
     discusses
    1.08
     examining
    1.06
     discussing
    1.04
     exploring
    0.98
     explored
    0.96
    Act Density 0.404%

    No Known Activations