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

    Neuronpedia

    INDEX
    Explanations

    references to famous personalities in entertainment, particularly related to their financial dealings

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

    specific names and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Callum
    -0.40
    aclk
    -0.35
    HostException
    -0.35
    accept
    -0.35
     hypo
    -0.34
     Cots
    -0.34
     Alp
    -0.34
     ec
    -0.33
     passionate
    -0.33
     richly
    -0.33
    POSITIVE LOGITS
    Britney
    1.85
     Spears
    1.81
     Britney
    1.74
    pears
    0.81
    atorship
    0.71
     Apes
    0.60
    NameInMap
    0.58
     препратки
    0.56
     nakalista
    0.56
    WithMany
    0.55
    Act Density 0.002%

    No Known Activations