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

    Neuronpedia

    INDEX
    Explanations

    reflexive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gospel
    -0.07
    小说
    -0.07
     Kür
    -0.07
     труд
    -0.06
     nuclear
    -0.06
    _ping
    -0.06
    perienced
    -0.06
     tribe
    -0.06
     охорони
    -0.06
    perial
    -0.06
    POSITIVE LOGITS
    ,array
    0.07
     debilitating
    0.06
     scenic
    0.06
    abra
    0.06
    .You
    0.06
    bob
    0.06
     Subset
    0.06
    番組
    0.06
    "}}>↵
    0.06
     RDD
    0.06
    Act Density 0.007%

    No Known Activations