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

    Neuronpedia

    INDEX
    Explanations

    references to gender-related employment issues

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

    Comes after certain words (it, can, serum)

    np_acts-logits-general · gemini-2.0-flash

    biological models and effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .",
    -1.05
    ."]
    -1.01
    NUMX
    -0.98
    ".
    -0.98
    .")
    -0.97
    .[/
    -0.96
    .’”
    -0.94
    .";
    -0.91
    `,
    -0.88
    ’.”
    -0.88
    POSITIVE LOGITS
     =
    0.89
     ppl
    0.87
     ->
    0.86
    :
    0.85
    !!
    0.83
    !!!!
    0.83
     &
    0.82
    !!!
    0.82
     govt
    0.81
    !!!!!
    0.76
    Act Density 0.253%

    No Known Activations