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

    Neuronpedia

    INDEX
    Explanations

    elements related to location and presence in context

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

    followed by forms of "to be" or "to have"

    np_acts-logits-general · gemini-2.0-flash

    reside or dwell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     here
    -0.53
    awaiter
    -0.50
    Fprintf
    -0.49
     in
    -0.49
     выйти
    -0.47
     dans
    -0.47
    gridy
    -0.46
     distanza
    -0.45
    在上
    -0.43
     في
    -0.42
    POSITIVE LOGITS
     resides
    0.96
     reside
    0.83
     resided
    0.81
     HasFactory
    0.73
     Roskov
    0.72
     congreg
    0.70
    Personendaten
    0.69
     قرار
    0.68
     dwells
    0.68
     domic
    0.67
    Act Density 0.304%

    No Known Activations