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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate titles or designations referring to notable individuals or entities

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

    the queen's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     frattempo
    -0.54
    neté
    -0.49
    middels
    -0.45
     snippetHide
    -0.45
    cheme
    -0.45
    ethical
    -0.44
    narrative
    -0.44
    JspWriter
    -0.43
     ſont
    -0.43
    kháu
    -0.43
    POSITIVE LOGITS
     pride
    0.45
     nicknamed
    0.44
     lenker
    0.39
    ThemeOverlay
    0.39
    bardziej
    0.39
     prides
    0.39
     considerada
    0.39
     considerado
    0.39
     regarded
    0.38
     considered
    0.38
    Act Density 0.054%

    No Known Activations