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

    Neuronpedia

    INDEX
    Explanations

    son or daughter of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ంట్
    0.39
     бизнеса
    0.39
     استخدم
    0.38
     आकर्षक
    0.38
     אטאטורק
    0.38
    িনবার্গ
    0.37
    Despatx
    0.37
    лянчук
    0.37
     CLIENTI
    0.37
     бизне
    0.36
    POSITIVE LOGITS
     daughter
    0.41
     of
    0.37
     son
    0.37
    -
    0.35
     sons
    0.35
     grandson
    0.35
    [
    0.35
    _
    0.35
     the
    0.34
    M
    0.34
    Act Density 0.064%

    No Known Activations