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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of people and organizations

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

    Capitalized word followed by a lowercase word

    np_acts-logits-general · gemini-2.0-flash

    names with specific endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urlpatterns
    -0.61
    __(/*!
    -0.51
    }{}
    -0.51
     dimaksud
    -0.51
     مورد
    -0.51
    __':
    -0.50
    |}{}
    -0.49
     econó
    -0.49
    mær
    -0.49
    __":
    -0.48
    POSITIVE LOGITS
    tagext
    0.69
    EndContext
    0.62
    ThroughAttribute
    0.61
     betweenstory
    0.60
     يتيمه
    0.56
    PropertyChanging
    0.55
     GenerationType
    0.53
    vasive
    0.53
    ⓧ
    0.53
    RepeatedField
    0.53
    Act Density 0.167%

    No Known Activations