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

    Neuronpedia

    INDEX
    Explanations

    references to women and female relatives

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

    women who reported

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ❋
    -0.47
     BoxFit
    -0.44
     Moscú
    -0.43
    хьтан
    -0.43
     BoxDecoration
    -0.41
     tartalomajánló
    -0.41
    gespräch
    -0.39
     exportación
    -0.39
     Lightboxes
    -0.37
     egna
    -0.37
    POSITIVE LOGITS
    GraphicsUnit
    0.55
     становника
    0.52
    webElement
    0.48
    fjspx
    0.45
    anneer
    0.45
    andaş
    0.44
    onResume
    0.44
    äsident
    0.44
    ‚¬
    0.43
    nodoc
    0.42
    Act Density 0.008%

    No Known Activations