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

    Neuronpedia

    INDEX
    Explanations

    belong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _feed
    -0.07
     M
    -0.07
    _CP
    -0.07
     censor
    -0.07
    _p
    -0.07
     Vaccine
    -0.07
     eliminates
    -0.07
     Impress
    -0.07
     cra
    -0.06
    Td
    -0.06
    POSITIVE LOGITS
     belonging
    0.09
     belong
    0.09
     принадлеж
    0.08
    属
    0.08
     belongs
    0.07
     belonged
    0.07
     ।↵↵
    0.07
    귀
    0.06
     Containers
    0.06
    ?>↵↵
    0.06
    Act Density 0.009%

    No Known Activations