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

    Neuronpedia

    INDEX
    Explanations

    references to specific populations or groups in societal contexts

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

    followed by prepositions or "the"

    np_acts-logits-general · gemini-2.0-flash

    actions and dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     is
    -0.36
     some
    -0.35
     itself
    -0.35
     auszu
    -0.34
    is
    -0.34
     einiges
    -0.33
     if
    -0.33
     again
    -0.33
    head
    -0.32
     case
    -0.32
    POSITIVE LOGITS
     którzy
    0.86
     kteří
    0.75
     queſta
    0.74
    Personendaten
    0.73
     ktorí
    0.73
    Controllo
    0.72
     Normdatei
    0.71
     marinho
    0.67
     незавершена
    0.65
    OGND
    0.65
    Act Density 0.678%

    No Known Activations