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

    Neuronpedia

    INDEX
    Explanations

    names of female characters or persons

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

    Names followed by last names or titles

    np_acts-logits-general · gemini-2.0-flash

    female given names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     himself
    -0.83
    AddTagHelper
    -0.71
     Himself
    -0.64
     Jr
    -0.62
     điển
    -0.62
     који
    -0.59
    himself
    -0.59
     nostru
    -0.57
    تقاوى
    -0.57
    providedIn
    -0.56
    POSITIVE LOGITS
     herself
    0.93
     Ann
    0.91
     Marie
    0.82
     bint
    0.82
    marie
    0.81
     Anne
    0.79
    beth
    0.79
    Ann
    0.75
     Louise
    0.74
    Marie
    0.72
    Act Density 0.112%

    No Known Activations