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

    Neuronpedia

    INDEX
    Explanations

    references to immediate family members, primarily offspring

    oai_token-act-pair · gemini-2.0-flash

    son

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     son
    -2.31
     daughter
    -2.19
     Daughter
    -1.90
    Son
    -1.84
    daughter
    -1.83
    Daughter
    -1.82
     Son
    -1.76
     sons
    -1.75
     daughters
    -1.75
     grandson
    -1.74
    POSITIVE LOGITS
    UNGE
    0.46
     na
    0.46
     di
    0.45
    itudine
    0.43
     "").
    0.43
     este
    0.42
    нави
    0.42
     &
    0.42
    ATELY
    0.42
     lección
    0.42
    Act Density 1.207%

    No Known Activations