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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experience and emotions related to motherhood

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

    Follows first-person pronouns expressing opinions

    np_acts-logits-general · gemini-2.0-flash

    pronoun followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     beginnetje
    -0.54
     सत्यापित
    -0.50
    PhysRevLett
    -0.47
    uudet
    -0.47
    нца
    -0.43
     beraber
    -0.43
    部は
    -0.43
    ้าน
    -0.43
    parsedMessage
    -0.42
     saman
    -0.42
    POSITIVE LOGITS
     often
    0.77
     think
    0.77
     feel
    0.77
     IBOutlet
    0.71
     GenerationType
    0.71
     always
    0.71
     feels
    0.69
    feel
    0.66
     nonatomic
    0.65
     rarely
    0.65
    Act Density 0.300%

    No Known Activations