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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and their associated relationships or roles within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Names followed by initials

    np_acts-logits-general · gemini-2.0-flash

    first names followed by last names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſelf
    -0.66
     Reſ
    -0.66
     Perſ
    -0.66
    ImageContext
    -0.65
    intios
    -0.65
     diſt
    -0.63
     raiſ
    -0.63
    RectangleBorder
    -0.63
     poffe
    -0.61
     faſt
    -0.59
    POSITIVE LOGITS
     N
    0.73
     Ny
    0.59
     Ngb
    0.55
    Nj
    0.54
    Mug
    0.53
     Ok
    0.53
     M
    0.52
     refugiados
    0.51
     Mut
    0.51
     NJ
    0.51
    Act Density 0.137%

    No Known Activations