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

    Neuronpedia

    INDEX
    Explanations

    words related to various societal roles and conditions

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

    "Everyone" or similar all-encompassing terms

    np_acts-logits-general · gemini-2.0-flash

    everyone knows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     misschien
    -0.64
     whole
    -0.64
     often
    -0.61
     spesso
    -0.59
     tutto
    -0.58
     all
    -0.55
     ganzen
    -0.55
     måske
    -0.55
     muchos
    -0.55
     hiç
    -0.54
    POSITIVE LOGITS
     except
    1.49
    except
    1.40
    Except
    1.28
     kecuali
    1.26
     Except
    1.24
     EXCEPT
    1.23
     excepto
    1.21
     đều
    1.20
     sauf
    1.18
     imaginable
    1.09
    Act Density 0.611%

    No Known Activations