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

    Neuronpedia

    INDEX
    Explanations

    terms related to gender and its classifications, particularly focusing on masculine and feminine qualities

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

    masculine and feminine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <![
    -0.42
    %^
    -0.41
    grès
    -0.41
     BorderSide
    -0.39
    rungsseite
    -0.38
    isière
    -0.38
    %[
    -0.37
    Muerte
    -0.37
    AddField
    -0.37
    WaitGroup
    -0.37
    POSITIVE LOGITS
     masculine
    1.73
    mascul
    1.58
     Mascul
    1.58
    Mascul
    1.40
     masculinity
    1.36
     masculin
    1.33
     feminine
    1.31
     Feminine
    1.24
     mascul
    1.22
     masculino
    1.16
    Act Density 0.006%

    No Known Activations