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

    Neuronpedia

    INDEX
    Explanations

    phrases related to academic or official titles and structures

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

    roles and official titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pizarra
    -0.44
     Económica
    -0.41
     península
    -0.37
     cafetería
    -0.36
     recomiendo
    -0.35
     gyhoeddwyd
    -0.35
     történ
    -0.35
     movilidad
    -0.35
     increíble
    -0.34
     pantai
    -0.34
    POSITIVE LOGITS
     Италијани
    0.60
     AttributeSet
    0.57
    djangoproject
    0.56
    AnimationsModule
    0.55
     Spinner
    0.54
     Caster
    0.53
     disc
    0.52
    人民共和国
    0.52
     badge
    0.51
    WaitGroup
    0.51
    Act Density 0.181%

    No Known Activations