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

    Neuronpedia

    INDEX
    Explanations

    could

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doubly
    -0.07
    {↵↵
    -0.07
     prominently
    -0.07
     turns
    -0.06
     Dich
    -0.06
     Obt
    -0.06
    err
    -0.06
    ?,
    -0.06
    tod
    -0.06
    -0.06
    POSITIVE LOGITS
    هـ
    0.07
    ฝ
    0.06
    ocities
    0.06
    ัณฑ
    0.06
    KB
    0.06
    .masks
    0.06
    _LARGE
    0.06
     눈
    0.06
     lượng
    0.06
     unthinkable
    0.06
    Act Density 0.184%

    No Known Activations