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

    Neuronpedia

    INDEX
    Explanations

    expressions of reflection and personal experience

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

    searching and wondering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Reſ
    -0.71
     Perſ
    -0.68
    GEBURTSDATUM
    -0.66
    TypedDataSet
    -0.66
     defaultstate
    -0.66
     للمعارف
    -0.62
     Италијани
    -0.62
     Conſ
    -0.60
     незавершена
    -0.60
     Jefus
    -0.60
    POSITIVE LOGITS
     decided
    0.52
     reminded
    0.51
     pondered
    0.50
     wondered
    0.48
     mused
    0.47
     remembered
    0.46
     thought
    0.45
     stumbled
    0.44
     instant
    0.43
     recently
    0.43
    Act Density 0.069%

    No Known Activations