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

    Neuronpedia

    INDEX
    Explanations

    busy moms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    0.77
    ل
    0.70
    0.66
    ")
    0.63
    т
    0.59
    Mun
    0.59
    Were
    0.58
    F
    0.54
     were
    0.54
    Moon
    0.53
    POSITIVE LOGITS
     mothers
    0.72
     dads
    0.71
    רי
    0.71
     moms
    0.71
     стаўкі
    0.70
    lių
    0.68
    li
    0.65
    mothers
    0.64
     WOMEN
    0.64
     PROBLEM
    0.63
    Act Density 0.001%

    No Known Activations