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

    Neuronpedia

    INDEX
    Explanations

    reat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     multip
    -0.09
     cosmetics
    -0.08
     numeric
    -0.08
     elective
    -0.08
     improv
    -0.08
     advert
    -0.08
     typical
    -0.08
     spontaneously
    -0.08
     fed
    -0.08
    semble
    -0.08
    POSITIVE LOGITS
    -grand
    0.11
     grandson
    0.11
     nephew
    0.11
     aunt
    0.11
     grandfather
    0.10
     niece
    0.10
     granddaughter
    0.10
    祖
    0.10
     Aunt
    0.10
     ancestors
    0.10
    Act Density 0.007%

    No Known Activations