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

    Neuronpedia

    INDEX
    Explanations

    mother and mothers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grandpa
    0.73
     Grandpa
    0.69
    grandfather
    0.67
    Daddy
    0.65
    Dad
    0.64
    Uncle
    0.63
    老爷
    0.62
    爷爷
    0.62
    爺
    0.61
    爸爸
    0.59
    POSITIVE LOGITS
     mother
    1.48
     Mother
    1.32
     moeder
    1.25
     mothers
    1.23
    mother
    1.22
     مادر
    1.20
     madre
    1.17
    Mother
    1.15
     motherhood
    1.14
     maternal
    1.13
    Act Density 0.011%

    No Known Activations