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

    Neuronpedia

    INDEX
    Explanations

    personal anecdotes, especially those about family but also about oneself

    oai_token-act-pair · gemini-2.0-flash

    family relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    antlr
    -0.51
     SwitchCompat
    -0.50
    baran
    -0.48
    ivores
    -0.47
    celotti
    -0.47
    SizeMode
    -0.47
    Биография
    -0.44
    Dias
    -0.44
    gway
    -0.44
    engar
    -0.44
    POSITIVE LOGITS
     my
    0.73
     <>",
    0.61
     daughter
    0.59
    odeficiency
    0.59
     wife
    0.59
     tartalomajánló
    0.59
     fiance
    0.58
     моих
    0.56
     dapp
    0.56
    #+#
    0.56
    Act Density 2.806%

    No Known Activations