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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and emotions

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

    "I" or "we" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    I created, we found, researchers have

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.80
    contentLoaded
    -0.80
     unknownFields
    -0.73
    Portály
    -0.69
    RTLI
    -0.68
     resourceCulture
    -0.66
    Personendaten
    -0.63
     Савезне
    -0.61
    ❹
    -0.61
     betweenstory
    -0.59
    POSITIVE LOGITS
     préfé
    0.54
     ContentValues
    0.52
    FetchType
    0.48
     Libros
    0.47
    selves
    0.46
     ArrayAdapter
    0.45
     Quien
    0.45
     omnia
    0.45
     Weimar
    0.45
     directly
    0.44
    Act Density 0.022%

    No Known Activations