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

    Neuronpedia

    INDEX
    Explanations

    reciprocity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ulang
    -0.08
     overw
    -0.07
    CUS
    -0.07
    -rays
    -0.07
     superbe
    -0.07
    /show
    -0.07
     eruption
    -0.07
    lict
    -0.07
     Eure
    -0.07
     탈
    -0.07
    POSITIVE LOGITS
     recipro
    0.11
     Reciprocity
    0.09
     reciproc
    0.09
     reciprocal
    0.08
     mú
    0.08
     resentment
    0.08
     plenamente
    0.08
     Recipro
    0.07
     निभ
    0.07
    .symmetric
    0.07
    Act Density 0.008%

    No Known Activations