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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, particularly in historical or biographical contexts

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

    First name initial followed by a period

    np_acts-logits-general · gemini-2.0-flash

    names followed by last names or initials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    webElementXpaths
    -0.86
    "):
    -0.84
    ])):
    -0.80
     виправивши
    -0.79
    twimg
    -0.78
     autorytatywna
    -0.78
    rungsseite
    -0.78
    '):
    -0.76
    دانشنامهٔ
    -0.74
    }")
    -0.72
    POSITIVE LOGITS
     "
    0.52
    Ashlee
    0.51
     Sr
    0.51
     “
    0.45
    醐
    0.45
     electrico
    0.42
    OfDay
    0.38
    ("
    0.38
    ıntı
    0.37
     Command
    0.37
    Act Density 0.031%

    No Known Activations