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

    Neuronpedia

    INDEX
    Explanations

    mentions of research studies and investigations, particularly concerning their objectives or findings

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

    context of this study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anges
    -0.48
     corne
    -0.47
     bes
    -0.47
     Canto
    -0.47
     Regex
    -0.46
     Rég
    -0.44
     coö
    -0.44
     betweenstory
    -0.43
     psycopg
    -0.43
     freq
    -0.43
    POSITIVE LOGITS
    ⓧ
    0.62
    ViewImports
    0.58
     grasas
    0.56
     huesos
    0.54
     estructuras
    0.53
     fieltro
    0.52
    RenderAtEndOf
    0.51
     cuenca
    0.50
     mercancías
    0.49
     obreros
    0.48
    Act Density 0.175%

    No Known Activations